June 2021 - Linux-stable-mirror

[PATCH 4.19] perf/core: Fix endless multiplex timer

by Wen Yang

From: Peter Zijlstra <peterz(a)infradead.org> [ Upstream commit 90c91dfb86d0ff545bd329d3ddd72c147e2ae198 ] Kan and Andi reported that we fail to kill rotation when the flexible events go empty, but the context does not. XXX moar Fixes: fd7d55172d1e ("perf/cgroups: Don't rotate events for cgroups unnecessarily") Reported-by: Andi Kleen <ak(a)linux.intel.com> Reported-by: Kan Liang <kan.liang(a)linux.intel.com> Tested-by: Kan Liang <kan.liang(a)linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Link: https://lkml.kernel.org/r/20200305123851.GX2596@hirez.programming.kicks-ass… Cc: <stable(a)vger.kernel.org> # 4.19 Signed-off-by: Wen Yang <wenyang(a)linux.alibaba.com> --- kernel/events/core.c | 20 ++++++++++++++------ 1 file changed, 14 insertions(+), 6 deletions(-) diff --git a/kernel/events/core.c b/kernel/events/core.c index 335fbde..0d60c82 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2081,6 +2081,7 @@ static inline int pmu_filter_match(struct perf_event *event) if (!ctx->nr_events && ctx->is_active) { ctx->is_active = 0; + ctx->rotate_necessary = 0; if (ctx->task) { WARN_ON_ONCE(cpuctx->task_ctx != ctx); cpuctx->task_ctx = NULL; @@ -2957,12 +2958,6 @@ static void ctx_sched_out(struct perf_event_context *ctx, if (!ctx->nr_active || !(is_active & EVENT_ALL)) return; - /* - * If we had been multiplexing, no rotations are necessary, now no events - * are active. - */ - ctx->rotate_necessary = 0; - perf_pmu_disable(ctx->pmu); if (is_active & EVENT_PINNED) { list_for_each_entry_safe(event, tmp, &ctx->pinned_active, active_list) @@ -2972,6 +2967,13 @@ static void ctx_sched_out(struct perf_event_context *ctx, if (is_active & EVENT_FLEXIBLE) { list_for_each_entry_safe(event, tmp, &ctx->flexible_active, active_list) group_sched_out(event, cpuctx, ctx); + + /* + * Since we cleared EVENT_FLEXIBLE, also clear + * rotate_necessary, is will be reset by + * ctx_flexible_sched_in() when needed. + */ + ctx->rotate_necessary = 0; } perf_pmu_enable(ctx->pmu); } @@ -3710,6 +3712,12 @@ static void rotate_ctx(struct perf_event_context *ctx, struct perf_event *event) typeof(*event), group_node); } + /* + * Unconditionally clear rotate_necessary; if ctx_flexible_sched_in() + * finds there are unschedulable events, it will set it again. + */ + ctx->rotate_necessary = 0; + return event; } -- 1.8.3.1

4 years

1
0
0 0

[PATCH] clk: Fix k210_clk_set_parent() in k210 driver

by Damien Le Moal

In k210_clk_set_parent(), add missing writel() call to update the mux register of a clock to change its parent. Fixes: c6ca7616f7d5 ("clk: Add RISC-V Canaan Kendryte K210 clock driver") Cc: stable(a)vger.kernel.org Signed-off-by: Damien Le Moal <damien.lemoal(a)wdc.com> --- drivers/clk/clk-k210.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/clk/clk-k210.c b/drivers/clk/clk-k210.c index 6c84abf5b2e3..67a7cb3503c3 100644 --- a/drivers/clk/clk-k210.c +++ b/drivers/clk/clk-k210.c @@ -722,6 +722,7 @@ static int k210_clk_set_parent(struct clk_hw *hw, u8 index) reg |= BIT(cfg->mux_bit); else reg &= ~BIT(cfg->mux_bit); + writel(reg, ksc->regs + cfg->mux_reg); spin_unlock_irqrestore(&ksc->clk_lock, flags); return 0; -- 2.31.1

4 years

1
0
0 0

URGENT RESPONDS NEEDED

by Mr. Ibrahim Abdoul

Dear Friend, My name is Mr. Ibrahim Abdoul. If the content of this message is contrary to your moral ethics, please accept my apology. But, please treat with absolute secrecy. I am working with one of the prime banks in Burkina Faso. Here in this bank existed a dormant account for many years, which belong to one of our late foreign customer. The amount in this account stands at $13,300,000.00 (Thirteen Million Three Hundred Thousand US Dollars). I was very fortunate to come across the deceased customer's security file during documentation of old and abandoned customer’s files for an official documentation and audit of the year 2020. I want a foreign account where the bank will transfer this fund. I know you would be surprised to read this message, especially from someone relatively unknown to you. But, do not worry yourself so much. This is a genuine, risk free and legal business transaction. All details shall be sent to you once I hear from you. If you are really sure of your sincerity, trustworthiness, accountability and confidentiality over this transaction, reply back to me urgently. cantact me on (mr.ibrahimabdoul2020(a)gmail.com) Best regards, Mr. Ibrahim Abdoul cantact me on (mr.ibrahimabdoul2020(a)gmail.com)

4 years

1
0
0 0

[PATCH] ceph: fix write_begin optimization when write is beyond EOF

by Jeff Layton

It's not sufficient to skip reading when the pos is beyond the EOF. There may be data at the head of the page that we need to fill in before the write. Only elide the read if the pos is beyond the last page in the file. Cc: <stable(a)vger.kernel.org> # v5.10 .. v5.12 Fixes: 1cc1699070bd ("ceph: fold ceph_update_writeable_page into ceph_write_begin") Reported-by: Andrew W Elble <aweits(a)rit.edu> Signed-off-by: Jeff Layton <jlayton(a)kernel.org> --- fs/ceph/addr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) Note to stable maintainers: This is needed in v5.10.z - v5.12.z. In v5.13, we've moved to using the new netfs_read_helper code so this isn't necessary there. I also now have a simple testcase for this that I'll submit to xfstests early next week. diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 26e66436f005..e636fb8275e1 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1353,11 +1353,11 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping, /* * In some cases we don't need to read at all: * - full page write - * - write that lies completely beyond EOF + * - write that lies in a page that is completely beyond EOF * - write that covers the the page from start to EOF or beyond it */ if ((pos_in_page == 0 && len == PAGE_SIZE) || - (pos >= i_size_read(inode)) || + (index > (i_size_read(inode) / PAGE_SIZE)) || (pos_in_page == 0 && (pos + len) >= i_size_read(inode))) { zero_user_segments(page, 0, pos_in_page, pos_in_page + len, PAGE_SIZE); -- 2.31.1

4 years

2
10
0 0

FAILED: patch "[PATCH] RDMA/mlx5: Use different doorbell memory for different" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From a0ffb4c12f7fa89163e228e6f27df09b46631db1 Mon Sep 17 00:00:00 2001 From: Mark Zhang <markzhang(a)nvidia.com> Date: Thu, 3 Jun 2021 16:18:03 +0300 Subject: [PATCH] RDMA/mlx5: Use different doorbell memory for different processes In a fork scenario, the parent and child can have same virtual address and also share the uverbs fd. That causes to the list_for_each_entry search return same doorbell physical page for all processes, even though that page has been COW' or copied. This patch takes the mm_struct into consideration during search, to make sure that VA's belonging to different processes are not intermixed. Resolves the malfunction of uverbs after fork in some specific cases. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Link: https://lore.kernel.org/r/feacc23fe0bc6e1088c6824d5583798745e72405.16227262… Reviewed-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: Mark Zhang <markzhang(a)nvidia.com> Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c index 61475b571531..7af4df7a6823 100644 --- a/drivers/infiniband/hw/mlx5/doorbell.c +++ b/drivers/infiniband/hw/mlx5/doorbell.c @@ -41,6 +41,7 @@ struct mlx5_ib_user_db_page { struct ib_umem *umem; unsigned long user_virt; int refcnt; + struct mm_struct *mm; }; int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, @@ -53,7 +54,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, mutex_lock(&context->db_page_mutex); list_for_each_entry(page, &context->db_page_list, list) - if (page->user_virt == (virt & PAGE_MASK)) + if ((current->mm == page->mm) && + (page->user_virt == (virt & PAGE_MASK))) goto found; page = kmalloc(sizeof(*page), GFP_KERNEL); @@ -71,6 +73,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, kfree(page); goto out; } + mmgrab(current->mm); + page->mm = current->mm; list_add(&page->list, &context->db_page_list); @@ -91,6 +95,7 @@ void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db) if (!--db->u.user_page->refcnt) { list_del(&db->u.user_page->list); + mmdrop(db->u.user_page->mm); ib_umem_release(db->u.user_page->umem); kfree(db->u.user_page); }

4 years

1
0
0 0

FAILED: patch "[PATCH] RDMA/mlx5: Use different doorbell memory for different" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From a0ffb4c12f7fa89163e228e6f27df09b46631db1 Mon Sep 17 00:00:00 2001 From: Mark Zhang <markzhang(a)nvidia.com> Date: Thu, 3 Jun 2021 16:18:03 +0300 Subject: [PATCH] RDMA/mlx5: Use different doorbell memory for different processes In a fork scenario, the parent and child can have same virtual address and also share the uverbs fd. That causes to the list_for_each_entry search return same doorbell physical page for all processes, even though that page has been COW' or copied. This patch takes the mm_struct into consideration during search, to make sure that VA's belonging to different processes are not intermixed. Resolves the malfunction of uverbs after fork in some specific cases. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Link: https://lore.kernel.org/r/feacc23fe0bc6e1088c6824d5583798745e72405.16227262… Reviewed-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: Mark Zhang <markzhang(a)nvidia.com> Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c index 61475b571531..7af4df7a6823 100644 --- a/drivers/infiniband/hw/mlx5/doorbell.c +++ b/drivers/infiniband/hw/mlx5/doorbell.c @@ -41,6 +41,7 @@ struct mlx5_ib_user_db_page { struct ib_umem *umem; unsigned long user_virt; int refcnt; + struct mm_struct *mm; }; int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, @@ -53,7 +54,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, mutex_lock(&context->db_page_mutex); list_for_each_entry(page, &context->db_page_list, list) - if (page->user_virt == (virt & PAGE_MASK)) + if ((current->mm == page->mm) && + (page->user_virt == (virt & PAGE_MASK))) goto found; page = kmalloc(sizeof(*page), GFP_KERNEL); @@ -71,6 +73,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, kfree(page); goto out; } + mmgrab(current->mm); + page->mm = current->mm; list_add(&page->list, &context->db_page_list); @@ -91,6 +95,7 @@ void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db) if (!--db->u.user_page->refcnt) { list_del(&db->u.user_page->list); + mmdrop(db->u.user_page->mm); ib_umem_release(db->u.user_page->umem); kfree(db->u.user_page); }

4 years

1
0
0 0

FAILED: patch "[PATCH] RDMA/mlx5: Use different doorbell memory for different" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From a0ffb4c12f7fa89163e228e6f27df09b46631db1 Mon Sep 17 00:00:00 2001 From: Mark Zhang <markzhang(a)nvidia.com> Date: Thu, 3 Jun 2021 16:18:03 +0300 Subject: [PATCH] RDMA/mlx5: Use different doorbell memory for different processes In a fork scenario, the parent and child can have same virtual address and also share the uverbs fd. That causes to the list_for_each_entry search return same doorbell physical page for all processes, even though that page has been COW' or copied. This patch takes the mm_struct into consideration during search, to make sure that VA's belonging to different processes are not intermixed. Resolves the malfunction of uverbs after fork in some specific cases. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Link: https://lore.kernel.org/r/feacc23fe0bc6e1088c6824d5583798745e72405.16227262… Reviewed-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: Mark Zhang <markzhang(a)nvidia.com> Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c index 61475b571531..7af4df7a6823 100644 --- a/drivers/infiniband/hw/mlx5/doorbell.c +++ b/drivers/infiniband/hw/mlx5/doorbell.c @@ -41,6 +41,7 @@ struct mlx5_ib_user_db_page { struct ib_umem *umem; unsigned long user_virt; int refcnt; + struct mm_struct *mm; }; int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, @@ -53,7 +54,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, mutex_lock(&context->db_page_mutex); list_for_each_entry(page, &context->db_page_list, list) - if (page->user_virt == (virt & PAGE_MASK)) + if ((current->mm == page->mm) && + (page->user_virt == (virt & PAGE_MASK))) goto found; page = kmalloc(sizeof(*page), GFP_KERNEL); @@ -71,6 +73,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, kfree(page); goto out; } + mmgrab(current->mm); + page->mm = current->mm; list_add(&page->list, &context->db_page_list); @@ -91,6 +95,7 @@ void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db) if (!--db->u.user_page->refcnt) { list_del(&db->u.user_page->list); + mmdrop(db->u.user_page->mm); ib_umem_release(db->u.user_page->umem); kfree(db->u.user_page); }

4 years

1
0
0 0

FAILED: patch "[PATCH] RDMA/mlx5: Use different doorbell memory for different" failed to apply to 4.14-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.14-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From a0ffb4c12f7fa89163e228e6f27df09b46631db1 Mon Sep 17 00:00:00 2001 From: Mark Zhang <markzhang(a)nvidia.com> Date: Thu, 3 Jun 2021 16:18:03 +0300 Subject: [PATCH] RDMA/mlx5: Use different doorbell memory for different processes In a fork scenario, the parent and child can have same virtual address and also share the uverbs fd. That causes to the list_for_each_entry search return same doorbell physical page for all processes, even though that page has been COW' or copied. This patch takes the mm_struct into consideration during search, to make sure that VA's belonging to different processes are not intermixed. Resolves the malfunction of uverbs after fork in some specific cases. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Link: https://lore.kernel.org/r/feacc23fe0bc6e1088c6824d5583798745e72405.16227262… Reviewed-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: Mark Zhang <markzhang(a)nvidia.com> Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c index 61475b571531..7af4df7a6823 100644 --- a/drivers/infiniband/hw/mlx5/doorbell.c +++ b/drivers/infiniband/hw/mlx5/doorbell.c @@ -41,6 +41,7 @@ struct mlx5_ib_user_db_page { struct ib_umem *umem; unsigned long user_virt; int refcnt; + struct mm_struct *mm; }; int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, @@ -53,7 +54,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, mutex_lock(&context->db_page_mutex); list_for_each_entry(page, &context->db_page_list, list) - if (page->user_virt == (virt & PAGE_MASK)) + if ((current->mm == page->mm) && + (page->user_virt == (virt & PAGE_MASK))) goto found; page = kmalloc(sizeof(*page), GFP_KERNEL); @@ -71,6 +73,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, kfree(page); goto out; } + mmgrab(current->mm); + page->mm = current->mm; list_add(&page->list, &context->db_page_list); @@ -91,6 +95,7 @@ void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db) if (!--db->u.user_page->refcnt) { list_del(&db->u.user_page->list); + mmdrop(db->u.user_page->mm); ib_umem_release(db->u.user_page->umem); kfree(db->u.user_page); }

4 years

1
0
0 0

FAILED: patch "[PATCH] RDMA/mlx5: Use different doorbell memory for different" failed to apply to 4.9-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.9-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From a0ffb4c12f7fa89163e228e6f27df09b46631db1 Mon Sep 17 00:00:00 2001 From: Mark Zhang <markzhang(a)nvidia.com> Date: Thu, 3 Jun 2021 16:18:03 +0300 Subject: [PATCH] RDMA/mlx5: Use different doorbell memory for different processes In a fork scenario, the parent and child can have same virtual address and also share the uverbs fd. That causes to the list_for_each_entry search return same doorbell physical page for all processes, even though that page has been COW' or copied. This patch takes the mm_struct into consideration during search, to make sure that VA's belonging to different processes are not intermixed. Resolves the malfunction of uverbs after fork in some specific cases. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Link: https://lore.kernel.org/r/feacc23fe0bc6e1088c6824d5583798745e72405.16227262… Reviewed-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: Mark Zhang <markzhang(a)nvidia.com> Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c index 61475b571531..7af4df7a6823 100644 --- a/drivers/infiniband/hw/mlx5/doorbell.c +++ b/drivers/infiniband/hw/mlx5/doorbell.c @@ -41,6 +41,7 @@ struct mlx5_ib_user_db_page { struct ib_umem *umem; unsigned long user_virt; int refcnt; + struct mm_struct *mm; }; int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, @@ -53,7 +54,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, mutex_lock(&context->db_page_mutex); list_for_each_entry(page, &context->db_page_list, list) - if (page->user_virt == (virt & PAGE_MASK)) + if ((current->mm == page->mm) && + (page->user_virt == (virt & PAGE_MASK))) goto found; page = kmalloc(sizeof(*page), GFP_KERNEL); @@ -71,6 +73,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, kfree(page); goto out; } + mmgrab(current->mm); + page->mm = current->mm; list_add(&page->list, &context->db_page_list); @@ -91,6 +95,7 @@ void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db) if (!--db->u.user_page->refcnt) { list_del(&db->u.user_page->list); + mmdrop(db->u.user_page->mm); ib_umem_release(db->u.user_page->umem); kfree(db->u.user_page); }

4 years

1
0
0 0

FAILED: patch "[PATCH] RDMA/mlx5: Use different doorbell memory for different" failed to apply to 4.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.4-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>. thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From a0ffb4c12f7fa89163e228e6f27df09b46631db1 Mon Sep 17 00:00:00 2001 From: Mark Zhang <markzhang(a)nvidia.com> Date: Thu, 3 Jun 2021 16:18:03 +0300 Subject: [PATCH] RDMA/mlx5: Use different doorbell memory for different processes In a fork scenario, the parent and child can have same virtual address and also share the uverbs fd. That causes to the list_for_each_entry search return same doorbell physical page for all processes, even though that page has been COW' or copied. This patch takes the mm_struct into consideration during search, to make sure that VA's belonging to different processes are not intermixed. Resolves the malfunction of uverbs after fork in some specific cases. Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") Link: https://lore.kernel.org/r/feacc23fe0bc6e1088c6824d5583798745e72405.16227262… Reviewed-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: Mark Zhang <markzhang(a)nvidia.com> Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c index 61475b571531..7af4df7a6823 100644 --- a/drivers/infiniband/hw/mlx5/doorbell.c +++ b/drivers/infiniband/hw/mlx5/doorbell.c @@ -41,6 +41,7 @@ struct mlx5_ib_user_db_page { struct ib_umem *umem; unsigned long user_virt; int refcnt; + struct mm_struct *mm; }; int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, @@ -53,7 +54,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, mutex_lock(&context->db_page_mutex); list_for_each_entry(page, &context->db_page_list, list) - if (page->user_virt == (virt & PAGE_MASK)) + if ((current->mm == page->mm) && + (page->user_virt == (virt & PAGE_MASK))) goto found; page = kmalloc(sizeof(*page), GFP_KERNEL); @@ -71,6 +73,8 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, kfree(page); goto out; } + mmgrab(current->mm); + page->mm = current->mm; list_add(&page->list, &context->db_page_list); @@ -91,6 +95,7 @@ void mlx5_ib_db_unmap_user(struct mlx5_ib_ucontext *context, struct mlx5_db *db) if (!--db->u.user_page->refcnt) { list_del(&db->u.user_page->list); + mmdrop(db->u.user_page->mm); ib_umem_release(db->u.user_page->umem); kfree(db->u.user_page); }

4 years

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror June 2021