- Linux-stable-mirror - lists.linaro.org

[PATCH 4/8] maple_tree: remove extra smp_wmb() from mas_dead_leaves()

by Liam R. Howlett

From: "Liam R. Howlett" <Liam.Howlett(a)Oracle.com> The call to mte_set_dead_node() before the smp_wmb() already calls smp_wmb() so this is not needed. This is an optimization for the RCU mode of the maple tree. Link: https://lkml.kernel.org/r/20230227173632.3292573-5-surenb@google.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Cc: stable(a)vger.kernel.org Signed-off-by: Liam Howlett <Liam.Howlett(a)oracle.com> --- lib/maple_tree.c | 1 - 1 file changed, 1 deletion(-) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 44d6ce30b28e..3d5ab02f981a 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5517,7 +5517,6 @@ unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots, break; mte_set_node_dead(entry); - smp_wmb(); /* Needed for RCU */ node->type = type; rcu_assign_pointer(slots[offset], node); } -- 2.39.2

2 years, 5 months

1
0
0 0

[PATCH 3/8] maple_tree: fix freeing of nodes in rcu mode

by Liam R. Howlett

From: "Liam R. Howlett" <Liam.Howlett(a)Oracle.com> The walk to destroy the nodes was not always setting the node type and would result in a destroy method potentially using the values as nodes. Avoid this by setting the correct node types. This is necessary for the RCU mode of the maple tree. Link: https://lkml.kernel.org/r/20230227173632.3292573-4-surenb@google.com Cc: <Stable(a)vger.kernel.org> Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> --- lib/maple_tree.c | 73 ++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 62 insertions(+), 11 deletions(-) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 089cd76ec379..44d6ce30b28e 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -902,6 +902,44 @@ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt, meta->end = end; } +/* + * mas_clear_meta() - clear the metadata information of a node, if it exists + * @mas: The maple state + * @mn: The maple node + * @mt: The maple node type + * @offset: The offset of the highest sub-gap in this node. + * @end: The end of the data in this node. + */ +static inline void mas_clear_meta(struct ma_state *mas, struct maple_node *mn, + enum maple_type mt) +{ + struct maple_metadata *meta; + unsigned long *pivots; + void __rcu **slots; + void *next; + + switch (mt) { + case maple_range_64: + pivots = mn->mr64.pivot; + if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) { + slots = mn->mr64.slot; + next = mas_slot_locked(mas, slots, + MAPLE_RANGE64_SLOTS - 1); + if (unlikely((mte_to_node(next) && mte_node_type(next)))) + return; /* The last slot is a node, no metadata */ + } + fallthrough; + case maple_arange_64: + meta = ma_meta(mn, mt); + break; + default: + return; + } + + meta->gap = 0; + meta->end = 0; +} + /* * ma_meta_end() - Get the data end of a node from the metadata * @mn: The maple node @@ -5455,20 +5493,22 @@ static inline int mas_rev_alloc(struct ma_state *mas, unsigned long min, * mas_dead_leaves() - Mark all leaves of a node as dead. * @mas: The maple state * @slots: Pointer to the slot array + * @type: The maple node type * * Must hold the write lock. * * Return: The number of leaves marked as dead. */ static inline -unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots) +unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots, + enum maple_type mt) { struct maple_node *node; enum maple_type type; void *entry; int offset; - for (offset = 0; offset < mt_slot_count(mas->node); offset++) { + for (offset = 0; offset < mt_slots[mt]; offset++) { entry = mas_slot_locked(mas, slots, offset); type = mte_node_type(entry); node = mte_to_node(entry); @@ -5487,14 +5527,13 @@ unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots) static void __rcu **mas_dead_walk(struct ma_state *mas, unsigned char offset) { - struct maple_node *node, *next; + struct maple_node *next; void __rcu **slots = NULL; next = mas_mn(mas); do { - mas->node = ma_enode_ptr(next); - node = mas_mn(mas); - slots = ma_slots(node, node->type); + mas->node = mt_mk_node(next, next->type); + slots = ma_slots(next, next->type); next = mas_slot_locked(mas, slots, offset); offset = 0; } while (!ma_is_leaf(next->type)); @@ -5558,11 +5597,14 @@ static inline void __rcu **mas_destroy_descend(struct ma_state *mas, node = mas_mn(mas); slots = ma_slots(node, mte_node_type(mas->node)); next = mas_slot_locked(mas, slots, 0); - if ((mte_dead_node(next))) + if ((mte_dead_node(next))) { + mte_to_node(next)->type = mte_node_type(next); next = mas_slot_locked(mas, slots, 1); + } mte_set_node_dead(mas->node); node->type = mte_node_type(mas->node); + mas_clear_meta(mas, node, node->type); node->piv_parent = prev; node->parent_slot = offset; offset = 0; @@ -5582,13 +5624,18 @@ static void mt_destroy_walk(struct maple_enode *enode, unsigned char ma_flags, MA_STATE(mas, &mt, 0, 0); - if (mte_is_leaf(enode)) + mas.node = enode; + if (mte_is_leaf(enode)) { + node->type = mte_node_type(enode); goto free_leaf; + } + ma_flags &= ~MT_FLAGS_LOCK_MASK; mt_init_flags(&mt, ma_flags); mas_lock(&mas); - mas.node = start = enode; + mte_to_node(enode)->ma_flags = ma_flags; + start = enode; slots = mas_destroy_descend(&mas, start, 0); node = mas_mn(&mas); do { @@ -5596,7 +5643,8 @@ static void mt_destroy_walk(struct maple_enode *enode, unsigned char ma_flags, unsigned char offset; struct maple_enode *parent, *tmp; - node->slot_len = mas_dead_leaves(&mas, slots); + node->type = mte_node_type(mas.node); + node->slot_len = mas_dead_leaves(&mas, slots, node->type); if (free) mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; @@ -5620,7 +5668,8 @@ static void mt_destroy_walk(struct maple_enode *enode, unsigned char ma_flags, } while (start != mas.node); node = mas_mn(&mas); - node->slot_len = mas_dead_leaves(&mas, slots); + node->type = mte_node_type(mas.node); + node->slot_len = mas_dead_leaves(&mas, slots, node->type); if (free) mt_free_bulk(node->slot_len, slots); @@ -5630,6 +5679,8 @@ static void mt_destroy_walk(struct maple_enode *enode, unsigned char ma_flags, free_leaf: if (free) mt_free_rcu(&node->rcu); + else + mas_clear_meta(&mas, node, node->type); } /* -- 2.39.2

2 years, 5 months

1
0
0 0

[PATCH 2/8] maple_tree: detect dead nodes in mas_start()

by Liam R. Howlett

From: "Liam R. Howlett" <Liam.Howlett(a)Oracle.com> When initially starting a search, the root node may already be in the process of being replaced in RCU mode. Detect and restart the walk if this is the case. This is necessary for RCU mode of the maple tree. Link: https://lkml.kernel.org/r/20230227173632.3292573-3-surenb@google.com Cc: <Stable(a)vger.kernel.org> Fixes: 54a611b60590 ("Maple Tree: add new data structure") Signed-off-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> --- lib/maple_tree.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index cc356b8369ad..089cd76ec379 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -1360,12 +1360,16 @@ static inline struct maple_enode *mas_start(struct ma_state *mas) mas->max = ULONG_MAX; mas->depth = 0; +retry: root = mas_root(mas); /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 1; mas->node = mte_safe_root(root); mas->offset = 0; + if (mte_dead_node(mas->node)) + goto retry; + return NULL; } -- 2.39.2

2 years, 5 months

1
0
0 0

[PATCH 1/8] maple_tree: be more cautious about dead nodes

by Liam R. Howlett

From: "Liam R. Howlett" <Liam.Howlett(a)Oracle.com> ma_pivots() and ma_data_end() may be called with a dead node. Ensure to that the node isn't dead before using the returned values. This is necessary for RCU mode of the maple tree. Link: https://lkml.kernel.org/r/20230227173632.3292573-1-surenb@google.com Link: https://lkml.kernel.org/r/20230227173632.3292573-2-surenb@google.com Fixes: 54a611b60590 ("Maple Tree: add new data structure") Cc: <Stable(a)vger.kernel.org> Signed-off-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> --- lib/maple_tree.c | 52 +++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 43 insertions(+), 9 deletions(-) diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 646297cae5d1..cc356b8369ad 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -544,6 +544,7 @@ static inline bool ma_dead_node(const struct maple_node *node) return (parent == node); } + /* * mte_dead_node() - check if the @enode is dead. * @enode: The encoded maple node @@ -625,6 +626,8 @@ static inline unsigned int mas_alloc_req(const struct ma_state *mas) * @node - the maple node * @type - the node type * + * In the event of a dead node, this array may be %NULL + * * Return: A pointer to the maple node pivots */ static inline unsigned long *ma_pivots(struct maple_node *node, @@ -1096,8 +1099,11 @@ static int mas_ascend(struct ma_state *mas) a_type = mas_parent_enum(mas, p_enode); a_node = mte_parent(p_enode); a_slot = mte_parent_slot(p_enode); - pivots = ma_pivots(a_node, a_type); a_enode = mt_mk_node(a_node, a_type); + pivots = ma_pivots(a_node, a_type); + + if (unlikely(ma_dead_node(a_node))) + return 1; if (!set_min && a_slot) { set_min = true; @@ -1401,6 +1407,9 @@ static inline unsigned char ma_data_end(struct maple_node *node, { unsigned char offset; + if (!pivots) + return 0; + if (type == maple_arange_64) return ma_meta_end(node, type); @@ -1436,6 +1445,9 @@ static inline unsigned char mas_data_end(struct ma_state *mas) return ma_meta_end(node, type); pivots = ma_pivots(node, type); + if (unlikely(ma_dead_node(node))) + return 0; + offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); @@ -4505,6 +4517,9 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min) node = mas_mn(mas); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); + if (unlikely(ma_dead_node(node))) + return 1; + mas->max = pivots[offset]; if (offset) mas->min = pivots[offset - 1] + 1; @@ -4526,6 +4541,9 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min) slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); offset = ma_data_end(node, mt, pivots, mas->max); + if (unlikely(ma_dead_node(node))) + return 1; + if (offset) mas->min = pivots[offset - 1] + 1; @@ -4574,6 +4592,7 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, struct maple_enode *enode; int level = 0; unsigned char offset; + unsigned char node_end; enum maple_type mt; void __rcu **slots; @@ -4597,7 +4616,11 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); - } while (unlikely(offset == ma_data_end(node, mt, pivots, mas->max))); + node_end = ma_data_end(node, mt, pivots, mas->max); + if (unlikely(ma_dead_node(node))) + return 1; + + } while (unlikely(offset == node_end)); slots = ma_slots(node, mt); pivot = mas_safe_pivot(mas, pivots, ++offset, mt); @@ -4613,6 +4636,9 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node, mt = mte_node_type(mas->node); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); + if (unlikely(ma_dead_node(node))) + return 1; + offset = 0; pivot = pivots[0]; } @@ -4659,11 +4685,14 @@ static inline void *mas_next_nentry(struct ma_state *mas, return NULL; } - pivots = ma_pivots(node, type); slots = ma_slots(node, type); - mas->index = mas_safe_min(mas, pivots, mas->offset); + pivots = ma_pivots(node, type); count = ma_data_end(node, type, pivots, mas->max); - if (ma_dead_node(node)) + if (unlikely(ma_dead_node(node))) + return NULL; + + mas->index = mas_safe_min(mas, pivots, mas->offset); + if (unlikely(ma_dead_node(node))) return NULL; if (mas->index > max) @@ -4817,6 +4846,11 @@ static inline void *mas_prev_nentry(struct ma_state *mas, unsigned long limit, slots = ma_slots(mn, mt); pivots = ma_pivots(mn, mt); + if (unlikely(ma_dead_node(mn))) { + mas_rewalk(mas, index); + goto retry; + } + if (offset == mt_pivots[mt]) pivot = mas->max; else @@ -6631,11 +6665,11 @@ static inline void *mas_first_entry(struct ma_state *mas, struct maple_node *mn, while (likely(!ma_is_leaf(mt))) { MT_BUG_ON(mas->tree, mte_dead_node(mas->node)); slots = ma_slots(mn, mt); - pivots = ma_pivots(mn, mt); - max = pivots[0]; entry = mas_slot(mas, slots, 0); + pivots = ma_pivots(mn, mt); if (unlikely(ma_dead_node(mn))) return NULL; + max = pivots[0]; mas->node = entry; mn = mas_mn(mas); mt = mte_node_type(mas->node); @@ -6655,13 +6689,13 @@ static inline void *mas_first_entry(struct ma_state *mas, struct maple_node *mn, if (likely(entry)) return entry; - pivots = ma_pivots(mn, mt); - mas->index = pivots[0] + 1; mas->offset = 1; entry = mas_slot(mas, slots, 1); + pivots = ma_pivots(mn, mt); if (unlikely(ma_dead_node(mn))) return NULL; + mas->index = pivots[0] + 1; if (mas->index > limit) goto none; -- 2.39.2

2 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] thunderbolt: Limit USB3 bandwidth of certain Intel USB4 host" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x f0a57dd33b3eadf540912cd130db727ea824d174 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '167993613776154(a)kroah.com' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: f0a57dd33b3e ("thunderbolt: Limit USB3 bandwidth of certain Intel USB4 host routers") 7af9da8ce8f9 ("thunderbolt: Add quirk to disable CLx") 6ce3563520be ("thunderbolt: Add support for DisplayPort bandwidth allocation mode") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f0a57dd33b3eadf540912cd130db727ea824d174 Mon Sep 17 00:00:00 2001 From: Gil Fine <gil.fine(a)linux.intel.com> Date: Tue, 31 Jan 2023 13:04:52 +0200 Subject: [PATCH] thunderbolt: Limit USB3 bandwidth of certain Intel USB4 host routers Current Intel USB4 host routers have hardware limitation that the USB3 bandwidth cannot go higher than 16376 Mb/s. Work this around by adding a new quirk that limits the bandwidth for the affected host routers. Cc: stable(a)vger.kernel.org Signed-off-by: Gil Fine <gil.fine(a)linux.intel.com> Signed-off-by: Mika Westerberg <mika.westerberg(a)linux.intel.com> diff --git a/drivers/thunderbolt/quirks.c b/drivers/thunderbolt/quirks.c index ae28a03fa890..1157b8869bcc 100644 --- a/drivers/thunderbolt/quirks.c +++ b/drivers/thunderbolt/quirks.c @@ -26,6 +26,19 @@ static void quirk_clx_disable(struct tb_switch *sw) tb_sw_dbg(sw, "disabling CL states\n"); } +static void quirk_usb3_maximum_bandwidth(struct tb_switch *sw) +{ + struct tb_port *port; + + tb_switch_for_each_port(sw, port) { + if (!tb_port_is_usb3_down(port)) + continue; + port->max_bw = 16376; + tb_port_dbg(port, "USB3 maximum bandwidth limited to %u Mb/s\n", + port->max_bw); + } +} + struct tb_quirk { u16 hw_vendor_id; u16 hw_device_id; @@ -43,6 +56,24 @@ static const struct tb_quirk tb_quirks[] = { * DP buffers. */ { 0x8087, 0x0b26, 0x0000, 0x0000, quirk_dp_credit_allocation }, + /* + * Limit the maximum USB3 bandwidth for the following Intel USB4 + * host routers due to a hardware issue. + */ + { 0x8087, PCI_DEVICE_ID_INTEL_ADL_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_ADL_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_RPL_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_RPL_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_M_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_P_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_P_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, /* * CLx is not supported on AMD USB4 Yellow Carp and Pink Sardine platforms. */ diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index b3cd13dc783b..275ff5219a3a 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -272,6 +272,8 @@ struct tb_bandwidth_group { * @group: Bandwidth allocation group the adapter is assigned to. Only * used for DP IN adapters for now. * @group_list: The adapter is linked to the group's list of ports through this + * @max_bw: Maximum possible bandwidth through this adapter if set to + * non-zero. * * In USB4 terminology this structure represents an adapter (protocol or * lane adapter). @@ -299,6 +301,7 @@ struct tb_port { unsigned int dma_credits; struct tb_bandwidth_group *group; struct list_head group_list; + unsigned int max_bw; }; /** diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 95ff02395822..6e87cf993c68 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -1882,6 +1882,15 @@ int usb4_port_retimer_nvm_read(struct tb_port *port, u8 index, usb4_port_retimer_nvm_read_block, &info); } +static inline unsigned int +usb4_usb3_port_max_bandwidth(const struct tb_port *port, unsigned int bw) +{ + /* Take the possible bandwidth limitation into account */ + if (port->max_bw) + return min(bw, port->max_bw); + return bw; +} + /** * usb4_usb3_port_max_link_rate() - Maximum support USB3 link rate * @port: USB3 adapter port @@ -1903,7 +1912,9 @@ int usb4_usb3_port_max_link_rate(struct tb_port *port) return ret; lr = (val & ADP_USB3_CS_4_MSLR_MASK) >> ADP_USB3_CS_4_MSLR_SHIFT; - return lr == ADP_USB3_CS_4_MSLR_20G ? 20000 : 10000; + ret = lr == ADP_USB3_CS_4_MSLR_20G ? 20000 : 10000; + + return usb4_usb3_port_max_bandwidth(port, ret); } /** @@ -1930,7 +1941,9 @@ int usb4_usb3_port_actual_link_rate(struct tb_port *port) return 0; lr = val & ADP_USB3_CS_4_ALR_MASK; - return lr == ADP_USB3_CS_4_ALR_20G ? 20000 : 10000; + ret = lr == ADP_USB3_CS_4_ALR_20G ? 20000 : 10000; + + return usb4_usb3_port_max_bandwidth(port, ret); } static int usb4_usb3_port_cm_request(struct tb_port *port, bool request)

2 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] thunderbolt: Limit USB3 bandwidth of certain Intel USB4 host" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x f0a57dd33b3eadf540912cd130db727ea824d174 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '167993613759241(a)kroah.com' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: f0a57dd33b3e ("thunderbolt: Limit USB3 bandwidth of certain Intel USB4 host routers") 7af9da8ce8f9 ("thunderbolt: Add quirk to disable CLx") 6ce3563520be ("thunderbolt: Add support for DisplayPort bandwidth allocation mode") aef9c693e7e5 ("thunderbolt: Move vendor specific NVM handling into nvm.c") 8b02b2da77c8 ("thunderbolt: Provide tb_retimer_nvm_read() analogous to tb_switch_nvm_read()") 7bfafaa5185b ("thunderbolt: Rename and make nvm_read() available for other files") 5424e1bf16f9 ("thunderbolt: Extend NVM version fields to 32-bits") 7f333ace0257 ("thunderbolt: Move tb_xdomain_parent() to tb.h") 3084b48fa139 ("thunderbolt: Change TMU mode to HiFi uni-directional once DisplayPort tunneled") 43f977bc60b1 ("thunderbolt: Enable CL0s for Intel Titan Ridge") 23ccd21ccb56 ("thunderbolt: Implement TMU time disruption for Intel Titan Ridge") 8a90e4fa3b4d ("thunderbolt: Add CL0s support for USB4 routers") a28ec0e165ba ("thunderbolt: Add TMU uni-directional mode") 43bddb26e20a ("thunderbolt: Tear down existing tunnels when resuming from hibernate") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f0a57dd33b3eadf540912cd130db727ea824d174 Mon Sep 17 00:00:00 2001 From: Gil Fine <gil.fine(a)linux.intel.com> Date: Tue, 31 Jan 2023 13:04:52 +0200 Subject: [PATCH] thunderbolt: Limit USB3 bandwidth of certain Intel USB4 host routers Current Intel USB4 host routers have hardware limitation that the USB3 bandwidth cannot go higher than 16376 Mb/s. Work this around by adding a new quirk that limits the bandwidth for the affected host routers. Cc: stable(a)vger.kernel.org Signed-off-by: Gil Fine <gil.fine(a)linux.intel.com> Signed-off-by: Mika Westerberg <mika.westerberg(a)linux.intel.com> diff --git a/drivers/thunderbolt/quirks.c b/drivers/thunderbolt/quirks.c index ae28a03fa890..1157b8869bcc 100644 --- a/drivers/thunderbolt/quirks.c +++ b/drivers/thunderbolt/quirks.c @@ -26,6 +26,19 @@ static void quirk_clx_disable(struct tb_switch *sw) tb_sw_dbg(sw, "disabling CL states\n"); } +static void quirk_usb3_maximum_bandwidth(struct tb_switch *sw) +{ + struct tb_port *port; + + tb_switch_for_each_port(sw, port) { + if (!tb_port_is_usb3_down(port)) + continue; + port->max_bw = 16376; + tb_port_dbg(port, "USB3 maximum bandwidth limited to %u Mb/s\n", + port->max_bw); + } +} + struct tb_quirk { u16 hw_vendor_id; u16 hw_device_id; @@ -43,6 +56,24 @@ static const struct tb_quirk tb_quirks[] = { * DP buffers. */ { 0x8087, 0x0b26, 0x0000, 0x0000, quirk_dp_credit_allocation }, + /* + * Limit the maximum USB3 bandwidth for the following Intel USB4 + * host routers due to a hardware issue. + */ + { 0x8087, PCI_DEVICE_ID_INTEL_ADL_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_ADL_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_RPL_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_RPL_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_M_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_P_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_P_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, /* * CLx is not supported on AMD USB4 Yellow Carp and Pink Sardine platforms. */ diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index b3cd13dc783b..275ff5219a3a 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -272,6 +272,8 @@ struct tb_bandwidth_group { * @group: Bandwidth allocation group the adapter is assigned to. Only * used for DP IN adapters for now. * @group_list: The adapter is linked to the group's list of ports through this + * @max_bw: Maximum possible bandwidth through this adapter if set to + * non-zero. * * In USB4 terminology this structure represents an adapter (protocol or * lane adapter). @@ -299,6 +301,7 @@ struct tb_port { unsigned int dma_credits; struct tb_bandwidth_group *group; struct list_head group_list; + unsigned int max_bw; }; /** diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 95ff02395822..6e87cf993c68 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -1882,6 +1882,15 @@ int usb4_port_retimer_nvm_read(struct tb_port *port, u8 index, usb4_port_retimer_nvm_read_block, &info); } +static inline unsigned int +usb4_usb3_port_max_bandwidth(const struct tb_port *port, unsigned int bw) +{ + /* Take the possible bandwidth limitation into account */ + if (port->max_bw) + return min(bw, port->max_bw); + return bw; +} + /** * usb4_usb3_port_max_link_rate() - Maximum support USB3 link rate * @port: USB3 adapter port @@ -1903,7 +1912,9 @@ int usb4_usb3_port_max_link_rate(struct tb_port *port) return ret; lr = (val & ADP_USB3_CS_4_MSLR_MASK) >> ADP_USB3_CS_4_MSLR_SHIFT; - return lr == ADP_USB3_CS_4_MSLR_20G ? 20000 : 10000; + ret = lr == ADP_USB3_CS_4_MSLR_20G ? 20000 : 10000; + + return usb4_usb3_port_max_bandwidth(port, ret); } /** @@ -1930,7 +1941,9 @@ int usb4_usb3_port_actual_link_rate(struct tb_port *port) return 0; lr = val & ADP_USB3_CS_4_ALR_MASK; - return lr == ADP_USB3_CS_4_ALR_20G ? 20000 : 10000; + ret = lr == ADP_USB3_CS_4_ALR_20G ? 20000 : 10000; + + return usb4_usb3_port_max_bandwidth(port, ret); } static int usb4_usb3_port_cm_request(struct tb_port *port, bool request)

2 years, 5 months

1
0
0 0

FAILED: patch "[PATCH] thunderbolt: Limit USB3 bandwidth of certain Intel USB4 host" failed to apply to 6.2-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.2-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.2.y git checkout FETCH_HEAD git cherry-pick -x f0a57dd33b3eadf540912cd130db727ea824d174 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '1679936136244141(a)kroah.com' --subject-prefix 'PATCH 6.2.y' HEAD^.. Possible dependencies: f0a57dd33b3e ("thunderbolt: Limit USB3 bandwidth of certain Intel USB4 host routers") 7af9da8ce8f9 ("thunderbolt: Add quirk to disable CLx") 6ce3563520be ("thunderbolt: Add support for DisplayPort bandwidth allocation mode") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f0a57dd33b3eadf540912cd130db727ea824d174 Mon Sep 17 00:00:00 2001 From: Gil Fine <gil.fine(a)linux.intel.com> Date: Tue, 31 Jan 2023 13:04:52 +0200 Subject: [PATCH] thunderbolt: Limit USB3 bandwidth of certain Intel USB4 host routers Current Intel USB4 host routers have hardware limitation that the USB3 bandwidth cannot go higher than 16376 Mb/s. Work this around by adding a new quirk that limits the bandwidth for the affected host routers. Cc: stable(a)vger.kernel.org Signed-off-by: Gil Fine <gil.fine(a)linux.intel.com> Signed-off-by: Mika Westerberg <mika.westerberg(a)linux.intel.com> diff --git a/drivers/thunderbolt/quirks.c b/drivers/thunderbolt/quirks.c index ae28a03fa890..1157b8869bcc 100644 --- a/drivers/thunderbolt/quirks.c +++ b/drivers/thunderbolt/quirks.c @@ -26,6 +26,19 @@ static void quirk_clx_disable(struct tb_switch *sw) tb_sw_dbg(sw, "disabling CL states\n"); } +static void quirk_usb3_maximum_bandwidth(struct tb_switch *sw) +{ + struct tb_port *port; + + tb_switch_for_each_port(sw, port) { + if (!tb_port_is_usb3_down(port)) + continue; + port->max_bw = 16376; + tb_port_dbg(port, "USB3 maximum bandwidth limited to %u Mb/s\n", + port->max_bw); + } +} + struct tb_quirk { u16 hw_vendor_id; u16 hw_device_id; @@ -43,6 +56,24 @@ static const struct tb_quirk tb_quirks[] = { * DP buffers. */ { 0x8087, 0x0b26, 0x0000, 0x0000, quirk_dp_credit_allocation }, + /* + * Limit the maximum USB3 bandwidth for the following Intel USB4 + * host routers due to a hardware issue. + */ + { 0x8087, PCI_DEVICE_ID_INTEL_ADL_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_ADL_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_RPL_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_RPL_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_M_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_P_NHI0, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, + { 0x8087, PCI_DEVICE_ID_INTEL_MTL_P_NHI1, 0x0000, 0x0000, + quirk_usb3_maximum_bandwidth }, /* * CLx is not supported on AMD USB4 Yellow Carp and Pink Sardine platforms. */ diff --git a/drivers/thunderbolt/tb.h b/drivers/thunderbolt/tb.h index b3cd13dc783b..275ff5219a3a 100644 --- a/drivers/thunderbolt/tb.h +++ b/drivers/thunderbolt/tb.h @@ -272,6 +272,8 @@ struct tb_bandwidth_group { * @group: Bandwidth allocation group the adapter is assigned to. Only * used for DP IN adapters for now. * @group_list: The adapter is linked to the group's list of ports through this + * @max_bw: Maximum possible bandwidth through this adapter if set to + * non-zero. * * In USB4 terminology this structure represents an adapter (protocol or * lane adapter). @@ -299,6 +301,7 @@ struct tb_port { unsigned int dma_credits; struct tb_bandwidth_group *group; struct list_head group_list; + unsigned int max_bw; }; /** diff --git a/drivers/thunderbolt/usb4.c b/drivers/thunderbolt/usb4.c index 95ff02395822..6e87cf993c68 100644 --- a/drivers/thunderbolt/usb4.c +++ b/drivers/thunderbolt/usb4.c @@ -1882,6 +1882,15 @@ int usb4_port_retimer_nvm_read(struct tb_port *port, u8 index, usb4_port_retimer_nvm_read_block, &info); } +static inline unsigned int +usb4_usb3_port_max_bandwidth(const struct tb_port *port, unsigned int bw) +{ + /* Take the possible bandwidth limitation into account */ + if (port->max_bw) + return min(bw, port->max_bw); + return bw; +} + /** * usb4_usb3_port_max_link_rate() - Maximum support USB3 link rate * @port: USB3 adapter port @@ -1903,7 +1912,9 @@ int usb4_usb3_port_max_link_rate(struct tb_port *port) return ret; lr = (val & ADP_USB3_CS_4_MSLR_MASK) >> ADP_USB3_CS_4_MSLR_SHIFT; - return lr == ADP_USB3_CS_4_MSLR_20G ? 20000 : 10000; + ret = lr == ADP_USB3_CS_4_MSLR_20G ? 20000 : 10000; + + return usb4_usb3_port_max_bandwidth(port, ret); } /** @@ -1930,7 +1941,9 @@ int usb4_usb3_port_actual_link_rate(struct tb_port *port) return 0; lr = val & ADP_USB3_CS_4_ALR_MASK; - return lr == ADP_USB3_CS_4_ALR_20G ? 20000 : 10000; + ret = lr == ADP_USB3_CS_4_ALR_20G ? 20000 : 10000; + + return usb4_usb3_port_max_bandwidth(port, ret); } static int usb4_usb3_port_cm_request(struct tb_port *port, bool request)

2 years, 5 months

1
0
0 0

[PATCH v3 4/4] KVM: arm64: Use config_lock to protect vgic state

by Oliver Upton

Almost all of the vgic state is VM-scoped but accessed from the context of a vCPU. These accesses were serialized on the kvm->lock which cannot be nested within a vcpu->mutex critical section. Move over the vgic state to using the config_lock. Tweak the lock ordering where necessary to ensure that the config_lock is acquired after the vcpu->mutex. Acquire the config_lock in kvm_vgic_create() to avoid a race between the converted flows and GIC creation. Where necessary, continue to acquire kvm->lock to avoid a race with vCPU creation (i.e. flows that use lock_all_vcpus()). Finally, promote the locking expectations in comments to lockdep assertions and update the locking documentation for the config_lock as well as vcpu->mutex. Cc: stable(a)vger.kernel.org Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> --- arch/arm64/kvm/vgic/vgic-debug.c | 8 ++--- arch/arm64/kvm/vgic/vgic-init.c | 36 ++++++++++++-------- arch/arm64/kvm/vgic/vgic-its.c | 18 ++++++---- arch/arm64/kvm/vgic/vgic-kvm-device.c | 47 ++++++++++++++++----------- arch/arm64/kvm/vgic/vgic-mmio-v3.c | 4 +-- arch/arm64/kvm/vgic/vgic-mmio.c | 12 +++---- arch/arm64/kvm/vgic/vgic-v4.c | 11 ++++--- arch/arm64/kvm/vgic/vgic.c | 12 ++++--- 8 files changed, 88 insertions(+), 60 deletions(-) diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c index 78cde687383c..07aa0437125a 100644 --- a/arch/arm64/kvm/vgic/vgic-debug.c +++ b/arch/arm64/kvm/vgic/vgic-debug.c @@ -85,7 +85,7 @@ static void *vgic_debug_start(struct seq_file *s, loff_t *pos) struct kvm *kvm = s->private; struct vgic_state_iter *iter; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); iter = kvm->arch.vgic.iter; if (iter) { iter = ERR_PTR(-EBUSY); @@ -104,7 +104,7 @@ static void *vgic_debug_start(struct seq_file *s, loff_t *pos) if (end_of_vgic(iter)) iter = NULL; out: - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); return iter; } @@ -132,12 +132,12 @@ static void vgic_debug_stop(struct seq_file *s, void *v) if (IS_ERR(v)) return; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); iter = kvm->arch.vgic.iter; kfree(iter->lpi_array); kfree(iter); kvm->arch.vgic.iter = NULL; - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); } static void print_dist_state(struct seq_file *s, struct vgic_dist *dist) diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index cd134db41a57..9d42c7cb2b58 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -74,9 +74,6 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) unsigned long i; int ret; - if (irqchip_in_kernel(kvm)) - return -EEXIST; - /* * This function is also called by the KVM_CREATE_IRQCHIP handler, * which had no chance yet to check the availability of the GICv2 @@ -87,10 +84,20 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) !kvm_vgic_global_state.can_emulate_gicv2) return -ENODEV; + /* Must be held to avoid race with vCPU creation */ + lockdep_assert_held(&kvm->lock); + ret = -EBUSY; if (!lock_all_vcpus(kvm)) return ret; + mutex_lock(&kvm->arch.config_lock); + + if (irqchip_in_kernel(kvm)) { + ret = -EEXIST; + goto out_unlock; + } + kvm_for_each_vcpu(i, vcpu, kvm) { if (vcpu_has_run_once(vcpu)) goto out_unlock; @@ -118,6 +125,7 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) INIT_LIST_HEAD(&kvm->arch.vgic.rd_regions); out_unlock: + mutex_unlock(&kvm->arch.config_lock); unlock_all_vcpus(kvm); return ret; } @@ -227,9 +235,9 @@ int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu) * KVM io device for the redistributor that belongs to this VCPU. */ if (dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); ret = vgic_register_redist_iodev(vcpu); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); } return ret; } @@ -250,7 +258,6 @@ static void kvm_vgic_vcpu_enable(struct kvm_vcpu *vcpu) * The function is generally called when nr_spis has been explicitly set * by the guest through the KVM DEVICE API. If not nr_spis is set to 256. * vgic_initialized() returns true when this function has succeeded. - * Must be called with kvm->lock held! */ int vgic_init(struct kvm *kvm) { @@ -259,6 +266,8 @@ int vgic_init(struct kvm *kvm) int ret = 0, i; unsigned long idx; + lockdep_assert_held(&kvm->arch.config_lock); + if (vgic_initialized(kvm)) return 0; @@ -373,12 +382,13 @@ void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu) vgic_cpu->rd_iodev.base_addr = VGIC_ADDR_UNDEF; } -/* To be called with kvm->lock held */ static void __kvm_vgic_destroy(struct kvm *kvm) { struct kvm_vcpu *vcpu; unsigned long i; + lockdep_assert_held(&kvm->arch.config_lock); + vgic_debug_destroy(kvm); kvm_for_each_vcpu(i, vcpu, kvm) @@ -389,9 +399,9 @@ static void __kvm_vgic_destroy(struct kvm *kvm) void kvm_vgic_destroy(struct kvm *kvm) { - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); __kvm_vgic_destroy(kvm); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); } /** @@ -414,9 +424,9 @@ int vgic_lazy_init(struct kvm *kvm) if (kvm->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V2) return -EBUSY; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); ret = vgic_init(kvm); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); } return ret; @@ -441,7 +451,7 @@ int kvm_vgic_map_resources(struct kvm *kvm) if (likely(vgic_ready(kvm))) return 0; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); if (vgic_ready(kvm)) goto out; @@ -459,7 +469,7 @@ int kvm_vgic_map_resources(struct kvm *kvm) dist->ready = true; out: - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index 2642e9ce2819..7713cd06104e 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -2045,6 +2045,13 @@ static int vgic_its_attr_regs_access(struct kvm_device *dev, mutex_lock(&dev->kvm->lock); + if (!lock_all_vcpus(dev->kvm)) { + mutex_unlock(&dev->kvm->lock); + return -EBUSY; + } + + mutex_lock(&dev->kvm->arch.config_lock); + if (IS_VGIC_ADDR_UNDEF(its->vgic_its_base)) { ret = -ENXIO; goto out; @@ -2058,11 +2065,6 @@ static int vgic_its_attr_regs_access(struct kvm_device *dev, goto out; } - if (!lock_all_vcpus(dev->kvm)) { - ret = -EBUSY; - goto out; - } - addr = its->vgic_its_base + offset; len = region->access_flags & VGIC_ACCESS_64bit ? 8 : 4; @@ -2076,8 +2078,9 @@ static int vgic_its_attr_regs_access(struct kvm_device *dev, } else { *reg = region->its_read(dev->kvm, its, addr, len); } - unlock_all_vcpus(dev->kvm); out: + mutex_unlock(&dev->kvm->arch.config_lock); + unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); return ret; } @@ -2757,6 +2760,8 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) return -EBUSY; } + mutex_lock(&kvm->arch.config_lock); + switch (attr) { case KVM_DEV_ARM_ITS_CTRL_RESET: vgic_its_reset(kvm, its); @@ -2769,6 +2774,7 @@ static int vgic_its_ctrl(struct kvm *kvm, struct vgic_its *its, u64 attr) break; } + mutex_unlock(&kvm->arch.config_lock); unlock_all_vcpus(kvm); mutex_unlock(&its->its_lock); mutex_unlock(&kvm->lock); diff --git a/arch/arm64/kvm/vgic/vgic-kvm-device.c b/arch/arm64/kvm/vgic/vgic-kvm-device.c index edeac2380591..07e727023deb 100644 --- a/arch/arm64/kvm/vgic/vgic-kvm-device.c +++ b/arch/arm64/kvm/vgic/vgic-kvm-device.c @@ -46,7 +46,7 @@ int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev struct vgic_dist *vgic = &kvm->arch.vgic; int r; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); switch (FIELD_GET(KVM_ARM_DEVICE_TYPE_MASK, dev_addr->id)) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); @@ -68,7 +68,7 @@ int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev r = -ENODEV; } - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); return r; } @@ -102,7 +102,7 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri if (get_user(addr, uaddr)) return -EFAULT; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); @@ -191,7 +191,7 @@ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool wri } out: - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); if (!r && !write) r = put_user(addr, uaddr); @@ -227,7 +227,7 @@ static int vgic_set_common_attr(struct kvm_device *dev, (val & 31)) return -EINVAL; - mutex_lock(&dev->kvm->lock); + mutex_lock(&dev->kvm->arch.config_lock); if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis) ret = -EBUSY; @@ -235,16 +235,16 @@ static int vgic_set_common_attr(struct kvm_device *dev, dev->kvm->arch.vgic.nr_spis = val - VGIC_NR_PRIVATE_IRQS; - mutex_unlock(&dev->kvm->lock); + mutex_unlock(&dev->kvm->arch.config_lock); return ret; } case KVM_DEV_ARM_VGIC_GRP_CTRL: { switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: - mutex_lock(&dev->kvm->lock); + mutex_lock(&dev->kvm->arch.config_lock); r = vgic_init(dev->kvm); - mutex_unlock(&dev->kvm->lock); + mutex_unlock(&dev->kvm->arch.config_lock); return r; case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: /* @@ -260,7 +260,10 @@ static int vgic_set_common_attr(struct kvm_device *dev, mutex_unlock(&dev->kvm->lock); return -EBUSY; } + + mutex_lock(&dev->kvm->arch.config_lock); r = vgic_v3_save_pending_tables(dev->kvm); + mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); return r; @@ -411,15 +414,17 @@ static int vgic_v2_attr_regs_access(struct kvm_device *dev, mutex_lock(&dev->kvm->lock); + if (!lock_all_vcpus(dev->kvm)) { + mutex_unlock(&dev->kvm->lock); + return -EBUSY; + } + + mutex_lock(&dev->kvm->arch.config_lock); + ret = vgic_init(dev->kvm); if (ret) goto out; - if (!lock_all_vcpus(dev->kvm)) { - ret = -EBUSY; - goto out; - } - switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: ret = vgic_v2_cpuif_uaccess(vcpu, is_write, addr, &val); @@ -432,8 +437,9 @@ static int vgic_v2_attr_regs_access(struct kvm_device *dev, break; } - unlock_all_vcpus(dev->kvm); out: + mutex_unlock(&dev->kvm->arch.config_lock); + unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && !is_write) @@ -569,12 +575,14 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev, mutex_lock(&dev->kvm->lock); - if (unlikely(!vgic_initialized(dev->kvm))) { - ret = -EBUSY; - goto out; + if (!lock_all_vcpus(dev->kvm)) { + mutex_unlock(&dev->kvm->lock); + return -EBUSY; } - if (!lock_all_vcpus(dev->kvm)) { + mutex_lock(&dev->kvm->arch.config_lock); + + if (unlikely(!vgic_initialized(dev->kvm))) { ret = -EBUSY; goto out; } @@ -609,8 +617,9 @@ static int vgic_v3_attr_regs_access(struct kvm_device *dev, break; } - unlock_all_vcpus(dev->kvm); out: + mutex_unlock(&dev->kvm->arch.config_lock); + unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && uaccess && !is_write) { diff --git a/arch/arm64/kvm/vgic/vgic-mmio-v3.c b/arch/arm64/kvm/vgic/vgic-mmio-v3.c index 91201f743033..472b18ac92a2 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio-v3.c +++ b/arch/arm64/kvm/vgic/vgic-mmio-v3.c @@ -111,7 +111,7 @@ static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu, case GICD_CTLR: { bool was_enabled, is_hwsgi; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); was_enabled = dist->enabled; is_hwsgi = dist->nassgireq; @@ -139,7 +139,7 @@ static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu, else if (!was_enabled && dist->enabled) vgic_kick_vcpus(vcpu->kvm); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); break; } case GICD_TYPER: diff --git a/arch/arm64/kvm/vgic/vgic-mmio.c b/arch/arm64/kvm/vgic/vgic-mmio.c index e67b3b2c8044..1939c94e0b24 100644 --- a/arch/arm64/kvm/vgic/vgic-mmio.c +++ b/arch/arm64/kvm/vgic/vgic-mmio.c @@ -530,13 +530,13 @@ unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 val; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); val = __vgic_mmio_read_active(vcpu, addr, len); vgic_access_active_finish(vcpu, intid); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); return val; } @@ -625,13 +625,13 @@ void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_cactive(vcpu, addr, len, val); vgic_access_active_finish(vcpu, intid); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); } int vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu, @@ -662,13 +662,13 @@ void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_sactive(vcpu, addr, len, val); vgic_access_active_finish(vcpu, intid); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); } int vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu, diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c index a413718be92b..3bb003478060 100644 --- a/arch/arm64/kvm/vgic/vgic-v4.c +++ b/arch/arm64/kvm/vgic/vgic-v4.c @@ -232,9 +232,8 @@ int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq) * @kvm: Pointer to the VM being initialized * * We may be called each time a vITS is created, or when the - * vgic is initialized. This relies on kvm->lock to be - * held. In both cases, the number of vcpus should now be - * fixed. + * vgic is initialized. In both cases, the number of vcpus + * should now be fixed. */ int vgic_v4_init(struct kvm *kvm) { @@ -243,6 +242,8 @@ int vgic_v4_init(struct kvm *kvm) int nr_vcpus, ret; unsigned long i; + lockdep_assert_held(&kvm->arch.config_lock); + if (!kvm_vgic_global_state.has_gicv4) return 0; /* Nothing to see here... move along. */ @@ -309,14 +310,14 @@ int vgic_v4_init(struct kvm *kvm) /** * vgic_v4_teardown - Free the GICv4 data structures * @kvm: Pointer to the VM being destroyed - * - * Relies on kvm->lock to be held. */ void vgic_v4_teardown(struct kvm *kvm) { struct its_vm *its_vm = &kvm->arch.vgic.its_vm; int i; + lockdep_assert_held(&kvm->arch.config_lock); + if (!its_vm->vpes) return; diff --git a/arch/arm64/kvm/vgic/vgic.c b/arch/arm64/kvm/vgic/vgic.c index d97e6080b421..0a005da83ae6 100644 --- a/arch/arm64/kvm/vgic/vgic.c +++ b/arch/arm64/kvm/vgic/vgic.c @@ -24,11 +24,13 @@ struct vgic_global kvm_vgic_global_state __ro_after_init = { /* * Locking order is always: * kvm->lock (mutex) - * its->cmd_lock (mutex) - * its->its_lock (mutex) - * vgic_cpu->ap_list_lock must be taken with IRQs disabled - * kvm->lpi_list_lock must be taken with IRQs disabled - * vgic_irq->irq_lock must be taken with IRQs disabled + * vcpu->mutex (mutex) + * kvm->arch.config_lock (mutex) + * its->cmd_lock (mutex) + * its->its_lock (mutex) + * vgic_cpu->ap_list_lock must be taken with IRQs disabled + * kvm->lpi_list_lock must be taken with IRQs disabled + * vgic_irq->irq_lock must be taken with IRQs disabled * * As the ap_list_lock might be taken from the timer interrupt handler, * we have to disable IRQs before taking this lock and everything lower -- 2.40.0.348.gf938b09366-goog

2 years, 5 months

1
0
0 0

[PATCH v3 3/4] KVM: arm64: Use config_lock to protect data ordered against KVM_RUN

by Oliver Upton

There are various bits of VM-scoped data that can only be configured before the first call to KVM_RUN, such as the hypercall bitmaps and the PMU. As these fields are protected by the kvm->lock and accessed while holding vcpu->mutex, this is yet another example of lock inversion. Change out the kvm->lock for kvm->arch.config_lock in all of these instances. Opportunistically simplify the locking mechanics of the PMU configuration by holding the config_lock for the entirety of kvm_arm_pmu_v3_set_attr(). Note that this also addresses a couple of bugs. There is an unguarded read of the PMU version in KVM_ARM_VCPU_PMU_V3_FILTER which could race with KVM_ARM_VCPU_PMU_V3_SET_PMU. Additionally, until now writes to the per-vCPU vPMU irq were not serialized VM-wide, meaning concurrent calls to KVM_ARM_VCPU_PMU_V3_IRQ could lead to a false positive in pmu_irq_is_valid(). Cc: stable(a)vger.kernel.org Tested-by: Jeremy Linton <jeremy.linton(a)arm.com> Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> --- arch/arm64/kvm/arm.c | 4 ++-- arch/arm64/kvm/guest.c | 2 ++ arch/arm64/kvm/hypercalls.c | 4 ++-- arch/arm64/kvm/pmu-emul.c | 23 ++++++----------------- 4 files changed, 12 insertions(+), 21 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 1620ec3d95ef..fd8d355aca15 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -624,9 +624,9 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) if (kvm_vm_is_protected(kvm)) kvm_call_hyp_nvhe(__pkvm_vcpu_init_traps, vcpu); - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); set_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags); - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index 07444fa22888..481c79cf22cd 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -957,7 +957,9 @@ int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, switch (attr->group) { case KVM_ARM_VCPU_PMU_V3_CTRL: + mutex_lock(&vcpu->kvm->arch.config_lock); ret = kvm_arm_pmu_v3_set_attr(vcpu, attr); + mutex_unlock(&vcpu->kvm->arch.config_lock); break; case KVM_ARM_VCPU_TIMER_CTRL: ret = kvm_arm_timer_set_attr(vcpu, attr); diff --git a/arch/arm64/kvm/hypercalls.c b/arch/arm64/kvm/hypercalls.c index 5da884e11337..fbdbf4257f76 100644 --- a/arch/arm64/kvm/hypercalls.c +++ b/arch/arm64/kvm/hypercalls.c @@ -377,7 +377,7 @@ static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val) if (val & ~fw_reg_features) return -EINVAL; - mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags) && val != *fw_reg_bmap) { @@ -387,7 +387,7 @@ static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val) WRITE_ONCE(*fw_reg_bmap, val); out: - mutex_unlock(&kvm->lock); + mutex_unlock(&kvm->arch.config_lock); return ret; } diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c index c243b10f3e15..82991d89c2ea 100644 --- a/arch/arm64/kvm/pmu-emul.c +++ b/arch/arm64/kvm/pmu-emul.c @@ -875,7 +875,7 @@ static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id) struct arm_pmu *arm_pmu; int ret = -ENXIO; - mutex_lock(&kvm->lock); + lockdep_assert_held(&kvm->arch.config_lock); mutex_lock(&arm_pmus_lock); list_for_each_entry(entry, &arm_pmus, entry) { @@ -895,7 +895,6 @@ static int kvm_arm_pmu_v3_set_pmu(struct kvm_vcpu *vcpu, int pmu_id) } mutex_unlock(&arm_pmus_lock); - mutex_unlock(&kvm->lock); return ret; } @@ -903,22 +902,20 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { struct kvm *kvm = vcpu->kvm; + lockdep_assert_held(&kvm->arch.config_lock); + if (!kvm_vcpu_has_pmu(vcpu)) return -ENODEV; if (vcpu->arch.pmu.created) return -EBUSY; - mutex_lock(&kvm->lock); if (!kvm->arch.arm_pmu) { /* No PMU set, get the default one */ kvm->arch.arm_pmu = kvm_pmu_probe_armpmu(); - if (!kvm->arch.arm_pmu) { - mutex_unlock(&kvm->lock); + if (!kvm->arch.arm_pmu) return -ENODEV; - } } - mutex_unlock(&kvm->lock); switch (attr->attr) { case KVM_ARM_VCPU_PMU_V3_IRQ: { @@ -962,19 +959,13 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) filter.action != KVM_PMU_EVENT_DENY)) return -EINVAL; - mutex_lock(&kvm->lock); - - if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags)) { - mutex_unlock(&kvm->lock); + if (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &kvm->arch.flags)) return -EBUSY; - } if (!kvm->arch.pmu_filter) { kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL_ACCOUNT); - if (!kvm->arch.pmu_filter) { - mutex_unlock(&kvm->lock); + if (!kvm->arch.pmu_filter) return -ENOMEM; - } /* * The default depends on the first applied filter. @@ -993,8 +984,6 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) else bitmap_clear(kvm->arch.pmu_filter, filter.base_event, filter.nevents); - mutex_unlock(&kvm->lock); - return 0; } case KVM_ARM_VCPU_PMU_V3_SET_PMU: { -- 2.40.0.348.gf938b09366-goog

2 years, 5 months

1
0
0 0

[PATCH v3 2/4] KVM: arm64: Avoid lock inversion when setting the VM register width

by Oliver Upton

kvm->lock must be taken outside of the vcpu->mutex. Of course, the locking documentation for KVM makes this abundantly clear. Nonetheless, the locking order in KVM/arm64 has been wrong for quite a while; we acquire the kvm->lock while holding the vcpu->mutex all over the shop. All was seemingly fine until commit 42a90008f890 ("KVM: Ensure lockdep knows about kvm->lock vs. vcpu->mutex ordering rule") caught us with our pants down, leading to lockdep barfing: ====================================================== WARNING: possible circular locking dependency detected 6.2.0-rc7+ #19 Not tainted ------------------------------------------------------ qemu-system-aar/859 is trying to acquire lock: ffff5aa69269eba0 (&host_kvm->lock){+.+.}-{3:3}, at: kvm_reset_vcpu+0x34/0x274 but task is already holding lock: ffff5aa68768c0b8 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x8c/0xba0 which lock already depends on the new lock. Add a dedicated lock to serialize writes to VM-scoped configuration from the context of a vCPU. Protect the register width flags with the new lock, thus avoiding the need to grab the kvm->lock while holding vcpu->mutex in kvm_reset_vcpu(). Cc: stable(a)vger.kernel.org Reported-by: Jeremy Linton <jeremy.linton(a)arm.com> Link: https://lore.kernel.org/kvmarm/f6452cdd-65ff-34b8-bab0-5c06416da5f6@arm.com/ Tested-by: Jeremy Linton <jeremy.linton(a)arm.com> Signed-off-by: Oliver Upton <oliver.upton(a)linux.dev> --- arch/arm64/include/asm/kvm_host.h | 3 +++ arch/arm64/kvm/arm.c | 18 ++++++++++++++++++ arch/arm64/kvm/reset.c | 6 +++--- 3 files changed, 24 insertions(+), 3 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 917586237a4d..cd1ef8716719 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -199,6 +199,9 @@ struct kvm_arch { /* Mandated version of PSCI */ u32 psci_version; + /* Protects VM-scoped configuration data */ + struct mutex config_lock; + /* * If we encounter a data abort without valid instruction syndrome * information, report this to user space. User space can (and diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 647798da8c41..1620ec3d95ef 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -128,6 +128,16 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) { int ret; + mutex_init(&kvm->arch.config_lock); + +#ifdef CONFIG_LOCKDEP + /* Clue in lockdep that the config_lock must be taken inside kvm->lock */ + mutex_lock(&kvm->lock); + mutex_lock(&kvm->arch.config_lock); + mutex_unlock(&kvm->arch.config_lock); + mutex_unlock(&kvm->lock); +#endif + ret = kvm_share_hyp(kvm, kvm + 1); if (ret) return ret; @@ -328,6 +338,14 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) spin_lock_init(&vcpu->arch.mp_state_lock); +#ifdef CONFIG_LOCKDEP + /* Inform lockdep that the config_lock is acquired after vcpu->mutex */ + mutex_lock(&vcpu->mutex); + mutex_lock(&vcpu->kvm->arch.config_lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); + mutex_unlock(&vcpu->mutex); +#endif + /* Force users to call KVM_ARM_VCPU_INIT */ vcpu->arch.target = -1; bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES); diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 9e023546bde0..b5dee8e57e77 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -205,7 +205,7 @@ static int kvm_set_vm_width(struct kvm_vcpu *vcpu) is32bit = vcpu_has_feature(vcpu, KVM_ARM_VCPU_EL1_32BIT); - lockdep_assert_held(&kvm->lock); + lockdep_assert_held(&kvm->arch.config_lock); if (test_bit(KVM_ARCH_FLAG_REG_WIDTH_CONFIGURED, &kvm->arch.flags)) { /* @@ -262,9 +262,9 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu) bool loaded; u32 pstate; - mutex_lock(&vcpu->kvm->lock); + mutex_lock(&vcpu->kvm->arch.config_lock); ret = kvm_set_vm_width(vcpu); - mutex_unlock(&vcpu->kvm->lock); + mutex_unlock(&vcpu->kvm->arch.config_lock); if (ret) return ret; -- 2.40.0.348.gf938b09366-goog

2 years, 5 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror