From 5558b92e8d39e18aa19619be2ee37274e9592528 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Sun, 26 Nov 2023 16:09:29 -0800 Subject: cxl/core: Always hold region_rwsem while reading poison lists A read of a device poison list is triggered via a sysfs attribute and the results are logged as kernel trace events of type cxl_poison. The work is managed by either: a) the region driver when one of more regions map the device, or by b) the memdev driver when no regions map the device. In the case of a) the region driver holds the region_rwsem while reading the poison by committed endpoint decoder mappings and for any unmapped resources. This makes sure that the cxl_poison trace event trace reports valid region info. (Region name, HPA, and UUID). In the case of b) the memdev driver holds the dpa_rwsem preventing new DPA resources from being attached to a region. However, it leaves a gap between region attach and decoder commit actions. If a DPA in the gap is in the poison list, the cxl_poison trace event will omit the region info. Close the gap by holding the region_rwsem and the dpa_rwsem when reading poison per memdev. Since both methods now hold both locks, down_read both from the caller. Doing so also addresses the lockdep assert that found this issue: Commit 458ba8189cb4 ("cxl: Add cxl_decoders_committed() helper") Fixes: f0832a586396 ("cxl/region: Provide region info to the cxl_poison trace event") Signed-off-by: Alison Schofield Reviewed-by: Davidlohr Bueso Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/08e8e7ec9a3413b91d51de39e385653494b1eed0.1701041440.git.alison.schofield@intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/memdev.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'drivers/cxl/core/memdev.c') diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index fc5c2b414793..5ad1b13e780a 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -227,10 +227,16 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) if (!port || !is_cxl_endpoint(port)) return -EINVAL; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + if (cxl_num_decoders_committed(port) == 0) { /* No regions mapped to this memdev */ rc = cxl_get_poison_by_memdev(cxlmd); @@ -239,6 +245,7 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd) rc = cxl_get_poison_by_endpoint(port); } up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } -- cgit v1.2.3-59-g8ed1b From 0e33ac9c3ffe5e4f55c68345f44cea7fec2fe750 Mon Sep 17 00:00:00 2001 From: Alison Schofield Date: Sun, 26 Nov 2023 16:09:30 -0800 Subject: cxl/memdev: Hold region_rwsem during inject and clear poison ops Poison inject and clear are supported via debugfs where a privileged user can inject and clear poison to a device physical address. Commit 458ba8189cb4 ("cxl: Add cxl_decoders_committed() helper") added a lockdep assert that highlighted a gap in poison inject and clear functions where holding the dpa_rwsem does not assure that a a DPA is not added to a region. The impact for inject and clear is that if the DPA address being injected or cleared has been attached to a region, but not yet committed, the dev_dbg() message intended to alert the debug user that they are acting on a mapped address is not emitted. Also, the cxl_poison trace event that serves as a log of the inject and clear activity will not include region info. Close this gap by snapshotting an unchangeable region state during poison inject and clear operations. That means holding both the region_rwsem and the dpa_rwsem during the inject and clear ops. Fixes: d2fbc4865802 ("cxl/memdev: Add support for the Inject Poison mailbox command") Fixes: 9690b07748d1 ("cxl/memdev: Add support for the Clear Poison mailbox command") Signed-off-by: Alison Schofield Reviewed-by: Davidlohr Bueso Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/08721dc1df0a51e4e38fecd02425c3475912dfd5.1701041440.git.alison.schofield@intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/memdev.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'drivers/cxl/core/memdev.c') diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c index 5ad1b13e780a..2f43d368ba07 100644 --- a/drivers/cxl/core/memdev.c +++ b/drivers/cxl/core/memdev.c @@ -331,10 +331,16 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + rc = cxl_validate_poison_dpa(cxlmd, dpa); if (rc) goto out; @@ -362,6 +368,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa) trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT); out: up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } @@ -379,10 +386,16 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) if (!IS_ENABLED(CONFIG_DEBUG_FS)) return 0; - rc = down_read_interruptible(&cxl_dpa_rwsem); + rc = down_read_interruptible(&cxl_region_rwsem); if (rc) return rc; + rc = down_read_interruptible(&cxl_dpa_rwsem); + if (rc) { + up_read(&cxl_region_rwsem); + return rc; + } + rc = cxl_validate_poison_dpa(cxlmd, dpa); if (rc) goto out; @@ -419,6 +432,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa) trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR); out: up_read(&cxl_dpa_rwsem); + up_read(&cxl_region_rwsem); return rc; } -- cgit v1.2.3-59-g8ed1b