From 2647c43c7f3ba4b752bfce261d53b16e2f5bc9e3 Mon Sep 17 00:00:00 2001 From: Mike Travis Date: Tue, 2 Oct 2018 13:01:46 -0500 Subject: x86/tsc: Fix UV TSC initialization The recent rework of the TSC calibration code introduced a regression on UV systems as it added a call to tsc_early_init() which initializes the TSC ADJUST values before acpi_boot_table_init(). In the case of UV systems, that is a necessary step that calls uv_system_init(). This informs tsc_sanitize_first_cpu() that the kernel runs on a platform with async TSC resets as documented in commit 341102c3ef29 ("x86/tsc: Add option that TSC on Socket 0 being non-zero is valid") Fix it by skipping the early tsc initialization on UV systems and let TSC init tests take place later in tsc_init(). Fixes: cf7a63ef4e02 ("x86/tsc: Calibrate tsc only once") Suggested-by: Hedi Berriche Signed-off-by: Mike Travis Signed-off-by: Thomas Gleixner Reviewed-by: Russ Anderson Reviewed-by: Dimitri Sivanich Cc: "H. Peter Anvin" Cc: Russ Anderson Cc: Dimitri Sivanich Cc: Borislav Petkov Cc: Kate Stewart Cc: Greg Kroah-Hartman Cc: Philippe Ombredanne Cc: Pavel Tatashin Cc: Peter Zijlstra Cc: Len Brown Cc: Dou Liyang Cc: Xiaoming Gao Cc: Rajvi Jingar Link: https://lkml.kernel.org/r/20181002180144.923579706@stormcage.americas.sgi.com --- arch/x86/kernel/tsc.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 6490f618e096..b52bd2b6cdb4 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -26,6 +26,7 @@ #include #include #include +#include unsigned int __read_mostly cpu_khz; /* TSC clocks / usec, not used here */ EXPORT_SYMBOL(cpu_khz); @@ -1433,6 +1434,9 @@ void __init tsc_early_init(void) { if (!boot_cpu_has(X86_FEATURE_TSC)) return; + /* Don't change UV TSC multi-chassis synchronization */ + if (is_early_uv_system()) + return; if (!determine_cpu_tsc_frequencies(true)) return; loops_per_jiffy = get_loops_per_jiffy(); -- cgit v1.2.3 From 88296bd42b4e9d24e138a68b337c235b5cac89a7 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Tue, 2 Oct 2018 15:45:11 -0700 Subject: x86/cpu/amd: Remove unnecessary parentheses Clang warns when multiple pairs of parentheses are used for a single conditional statement. arch/x86/kernel/cpu/amd.c:925:14: warning: equality comparison with extraneous parentheses [-Wparentheses-equality] if ((c->x86 == 6)) { ~~~~~~~^~~~ arch/x86/kernel/cpu/amd.c:925:14: note: remove extraneous parentheses around the comparison to silence this warning if ((c->x86 == 6)) { ~ ^ ~ arch/x86/kernel/cpu/amd.c:925:14: note: use '=' to turn this equality comparison into an assignment if ((c->x86 == 6)) { ^~ = 1 warning generated. Signed-off-by: Nathan Chancellor Cc: Borislav Petkov Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181002224511.14929-1-natechancellor@gmail.com Link: https://github.com/ClangBuiltLinux/linux/issues/187 Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/amd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 22ab408177b2..eeea634bee0a 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -922,7 +922,7 @@ static void init_amd(struct cpuinfo_x86 *c) static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size) { /* AMD errata T13 (order #21922) */ - if ((c->x86 == 6)) { + if (c->x86 == 6) { /* Duron Rev A0 */ if (c->x86_model == 3 && c->x86_stepping == 0) size = 64; -- cgit v1.2.3 From 53ed74af05517cf5fe83d87c4bb7ab998adfd631 Mon Sep 17 00:00:00 2001 From: Reinette Chatre Date: Wed, 19 Sep 2018 10:29:11 -0700 Subject: x86/intel_rdt: Re-enable pseudo-lock measurements Commit 4a7a54a55e72 ("x86/intel_rdt: Disable PMU access") disabled measurements of pseudo-locked regions because of incorrect usage of the performance monitoring hardware. Cache pseudo-locking measurements are now done correctly with the in-kernel perf API and its use can be re-enabled at this time. The adjustment to the in-kernel perf API also separated the L2 and L3 measurements that can be triggered separately from user space. The re-enabling of the measurements is thus not a simple revert of the original disable in order to accommodate the additional parameter possible. Signed-off-by: Reinette Chatre Signed-off-by: Thomas Gleixner Cc: fenghua.yu@intel.com Cc: tony.luck@intel.com Cc: peterz@infradead.org Cc: acme@kernel.org Cc: gavin.hindman@intel.com Cc: jithu.joseph@intel.com Cc: dave.hansen@intel.com Cc: hpa@zytor.com Link: https://lkml.kernel.org/r/bfb9fc31692e0c62d9ca39062e55eceb6a0635b5.1537377064.git.reinette.chatre@intel.com --- arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c index d68836139cf9..30e6c9f5a0ad 100644 --- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c @@ -1236,7 +1236,7 @@ static ssize_t pseudo_lock_measure_trigger(struct file *file, buf[buf_size] = '\0'; ret = kstrtoint(buf, 10, &sel); if (ret == 0) { - if (sel != 1) + if (sel != 1 && sel != 2 && sel != 3) return -EINVAL; ret = debugfs_file_get(file->f_path.dentry); if (ret) -- cgit v1.2.3 From 82159876d32b7959c0b0ea8fe12c428f41502a6f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Thu, 30 Aug 2018 14:50:39 +0300 Subject: x86/intel_rdt: Switch to bitmap_zalloc() Switch to bitmap_zalloc() to show clearly what is allocated. Besides that it returns a pointer of bitmap type instead of opaque void *. Signed-off-by: Andy Shevchenko Signed-off-by: Thomas Gleixner Acked-by: Fenghua Yu Cc: "H. Peter Anvin" Link: https://lkml.kernel.org/r/20180830115039.63430-1-andriy.shevchenko@linux.intel.com --- arch/x86/kernel/cpu/intel_rdt.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index abb71ac70443..1214f3f7ec6d 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -485,9 +485,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) size_t tsize; if (is_llc_occupancy_enabled()) { - d->rmid_busy_llc = kcalloc(BITS_TO_LONGS(r->num_rmid), - sizeof(unsigned long), - GFP_KERNEL); + d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL); if (!d->rmid_busy_llc) return -ENOMEM; INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); @@ -496,7 +494,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) tsize = sizeof(*d->mbm_total); d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); if (!d->mbm_total) { - kfree(d->rmid_busy_llc); + bitmap_free(d->rmid_busy_llc); return -ENOMEM; } } @@ -504,7 +502,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) tsize = sizeof(*d->mbm_local); d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); if (!d->mbm_local) { - kfree(d->rmid_busy_llc); + bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); return -ENOMEM; } @@ -612,7 +610,7 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) kfree(d->ctrl_val); kfree(d->mbps_val); - kfree(d->rmid_busy_llc); + bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); kfree(d->mbm_local); kfree(d); -- cgit v1.2.3 From 2cc81c6992248ea37d0241bc325977bab310bc3b Mon Sep 17 00:00:00 2001 From: Xiaochen Shen Date: Wed, 12 Sep 2018 16:48:38 -0700 Subject: x86/intel_rdt: Show missing resctrl mount options In resctrl filesystem, mount options exist to enable L3/L2 CDP and MBA Software Controller features if the platform supports them: mount -t resctrl resctrl [-o cdp[,cdpl2][,mba_MBps]] /sys/fs/resctrl But currently only "cdp" option is displayed in /proc/mounts. "cdpl2" and "mba_MBps" options are not shown even when they are active. Before: # mount -t resctrl resctrl -o cdp,mba_MBps /sys/fs/resctrl # grep resctrl /proc/mounts /sys/fs/resctrl /sys/fs/resctrl resctrl rw,relatime,cdp 0 0 After: # mount -t resctrl resctrl -o cdp,mba_MBps /sys/fs/resctrl # grep resctrl /proc/mounts /sys/fs/resctrl /sys/fs/resctrl resctrl rw,relatime,cdp,mba_MBps 0 0 Signed-off-by: Xiaochen Shen Signed-off-by: Fenghua Yu Signed-off-by: Thomas Gleixner Cc: "H Peter Anvin" Cc: "Tony Luck" Link: https://lkml.kernel.org/r/1536796118-60135-1-git-send-email-fenghua.yu@intel.com --- arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 1b8e86a5d5e1..82a487840eb2 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -2795,6 +2795,13 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) { if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled) seq_puts(seq, ",cdp"); + + if (rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) + seq_puts(seq, ",cdpl2"); + + if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA])) + seq_puts(seq, ",mba_MBps"); + return 0; } -- cgit v1.2.3 From 49e00eee00612b1357596fed8a88b621a7648c14 Mon Sep 17 00:00:00 2001 From: Reinette Chatre Date: Thu, 4 Oct 2018 14:05:23 -0700 Subject: x86/intel_rdt: Fix out-of-bounds memory access in CBM tests While the DOC at the beginning of lib/bitmap.c explicitly states that "The number of valid bits in a given bitmap does _not_ need to be an exact multiple of BITS_PER_LONG.", some of the bitmap operations do indeed access BITS_PER_LONG portions of the provided bitmap no matter the size of the provided bitmap. For example, if bitmap_intersects() is provided with an 8 bit bitmap the operation will access BITS_PER_LONG bits from the provided bitmap. While the operation ensures that these extra bits do not affect the result, the memory is still accessed. The capacity bitmasks (CBMs) are typically stored in u32 since they can never exceed 32 bits. A few instances exist where a bitmap_* operation is performed on a CBM by simply pointing the bitmap operation to the stored u32 value. The consequence of this pattern is that some bitmap_* operations will access out-of-bounds memory when interacting with the provided CBM. This is confirmed with a KASAN test that reports: BUG: KASAN: stack-out-of-bounds in __bitmap_intersects+0xa2/0x100 and BUG: KASAN: stack-out-of-bounds in __bitmap_weight+0x58/0x90 Fix this by moving any CBM provided to a bitmap operation needing BITS_PER_LONG to an 'unsigned long' variable. [ tglx: Changed related function arguments to unsigned long and got rid of the _cbm extra step ] Fixes: 72d505056604 ("x86/intel_rdt: Add utilities to test pseudo-locked region possibility") Fixes: 49f7b4efa110 ("x86/intel_rdt: Enable setting of exclusive mode") Fixes: d9b48c86eb38 ("x86/intel_rdt: Display resource groups' allocations' size in bytes") Fixes: 95f0b77efa57 ("x86/intel_rdt: Initialize new resource group with sane defaults") Signed-off-by: Reinette Chatre Signed-off-by: Thomas Gleixner Cc: fenghua.yu@intel.com Cc: tony.luck@intel.com Cc: gavin.hindman@intel.com Cc: jithu.joseph@intel.com Cc: dave.hansen@intel.com Cc: hpa@zytor.com Link: https://lkml.kernel.org/r/69a428613a53f10e80594679ac726246020ff94f.1538686926.git.reinette.chatre@intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel_rdt.h | 6 ++--- arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 20 ++++++++-------- arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 36 ++++++++++++++++++----------- 3 files changed, 37 insertions(+), 25 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h index 285eb3ec4200..3736f6dc9545 100644 --- a/arch/x86/kernel/cpu/intel_rdt.h +++ b/arch/x86/kernel/cpu/intel_rdt.h @@ -529,14 +529,14 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, int rdtgroup_schemata_show(struct kernfs_open_file *of, struct seq_file *s, void *v); bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - u32 _cbm, int closid, bool exclusive); + unsigned long cbm, int closid, bool exclusive); unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d, - u32 cbm); + unsigned long cbm); enum rdtgrp_mode rdtgroup_mode_by_closid(int closid); int rdtgroup_tasks_assigned(struct rdtgroup *r); int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp); int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp); -bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm); +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm); bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d); int rdt_pseudo_lock_init(void); void rdt_pseudo_lock_release(void); diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c index 40f3903ae5d9..f8c260d522ca 100644 --- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c @@ -797,25 +797,27 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) /** * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked * @d: RDT domain - * @_cbm: CBM to test + * @cbm: CBM to test * - * @d represents a cache instance and @_cbm a capacity bitmask that is - * considered for it. Determine if @_cbm overlaps with any existing + * @d represents a cache instance and @cbm a capacity bitmask that is + * considered for it. Determine if @cbm overlaps with any existing * pseudo-locked region on @d. * - * Return: true if @_cbm overlaps with pseudo-locked region on @d, false + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * + * Return: true if @cbm overlaps with pseudo-locked region on @d, false * otherwise. */ -bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm) +bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm) { - unsigned long *cbm = (unsigned long *)&_cbm; - unsigned long *cbm_b; unsigned int cbm_len; + unsigned long cbm_b; if (d->plr) { cbm_len = d->plr->r->cache.cbm_len; - cbm_b = (unsigned long *)&d->plr->cbm; - if (bitmap_intersects(cbm, cbm_b, cbm_len)) + cbm_b = d->plr->cbm; + if (bitmap_intersects(&cbm, &cbm_b, cbm_len)) return true; } return false; diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 1b8e86a5d5e1..b140c68bc14b 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -975,33 +975,34 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, * is false then overlaps with any resource group or hardware entities * will be considered. * + * @cbm is unsigned long, even if only 32 bits are used, to make the + * bitmap functions work correctly. + * * Return: false if CBM does not overlap, true if it does. */ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - u32 _cbm, int closid, bool exclusive) + unsigned long cbm, int closid, bool exclusive) { - unsigned long *cbm = (unsigned long *)&_cbm; - unsigned long *ctrl_b; enum rdtgrp_mode mode; + unsigned long ctrl_b; u32 *ctrl; int i; /* Check for any overlap with regions used by hardware directly */ if (!exclusive) { - if (bitmap_intersects(cbm, - (unsigned long *)&r->cache.shareable_bits, - r->cache.cbm_len)) + ctrl_b = r->cache.shareable_bits; + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) return true; } /* Check for overlap with other resource groups */ ctrl = d->ctrl_val; for (i = 0; i < closids_supported(); i++, ctrl++) { - ctrl_b = (unsigned long *)ctrl; + ctrl_b = *ctrl; mode = rdtgroup_mode_by_closid(i); if (closid_allocated(i) && i != closid && mode != RDT_MODE_PSEUDO_LOCKSETUP) { - if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) { + if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) { if (exclusive) { if (mode == RDT_MODE_EXCLUSIVE) return true; @@ -1138,15 +1139,18 @@ out: * computed by first dividing the total cache size by the CBM length to * determine how many bytes each bit in the bitmask represents. The result * is multiplied with the number of bits set in the bitmask. + * + * @cbm is unsigned long, even if only 32 bits are used to make the + * bitmap functions work correctly. */ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, - struct rdt_domain *d, u32 cbm) + struct rdt_domain *d, unsigned long cbm) { struct cpu_cacheinfo *ci; unsigned int size = 0; int num_b, i; - num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len); + num_b = bitmap_weight(&cbm, r->cache.cbm_len); ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask)); for (i = 0; i < ci->num_leaves; i++) { if (ci->info_list[i].level == r->cache_level) { @@ -2353,6 +2357,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) u32 used_b = 0, unused_b = 0; u32 closid = rdtgrp->closid; struct rdt_resource *r; + unsigned long tmp_cbm; enum rdtgrp_mode mode; struct rdt_domain *d; int i, ret; @@ -2390,9 +2395,14 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) * modify the CBM based on system availability. */ cbm_ensure_valid(&d->new_ctrl, r); - if (bitmap_weight((unsigned long *) &d->new_ctrl, - r->cache.cbm_len) < - r->cache.min_cbm_bits) { + /* + * Assign the u32 CBM to an unsigned long to ensure + * that bitmap_weight() does not access out-of-bound + * memory. + */ + tmp_cbm = d->new_ctrl; + if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < + r->cache.min_cbm_bits) { rdt_last_cmd_printf("no space on %s:%d\n", r->name, d->id); return -ENOSPC; -- cgit v1.2.3 From 521348b011d64cf3febb10b64ba5b472681bef94 Mon Sep 17 00:00:00 2001 From: Reinette Chatre Date: Wed, 3 Oct 2018 15:17:01 -0700 Subject: x86/intel_rdt: Introduce utility to obtain CDP peer Introduce a utility that, when provided with a RDT resource and an instance of this RDT resource (a RDT domain), would return pointers to the RDT resource and RDT domain that share the same hardware. This is specific to the CDP resources that share the same hardware. For example, if a pointer to the RDT_RESOURCE_L2DATA resource (struct rdt_resource) and a pointer to an instance of this resource (struct rdt_domain) is provided, then it will return a pointer to the RDT_RESOURCE_L2CODE resource as well as the specific instance that shares the same hardware as the provided rdt_domain. This utility is created in support of the "exclusive" resource group mode where overlap of resource allocation between resource groups need to be avoided. The overlap test need to consider not just the matching resources, but also the resources that share the same hardware. Temporarily mark it as unused in support of patch testing to avoid compile warnings until it is used. Fixes: 49f7b4efa110 ("x86/intel_rdt: Enable setting of exclusive mode") Signed-off-by: Reinette Chatre Signed-off-by: Thomas Gleixner Tested-by: Jithu Joseph Acked-by: Fenghua Yu Cc: tony.luck@intel.com Cc: gavin.hindman@intel.com Cc: dave.hansen@intel.com Cc: hpa@zytor.com Link: https://lkml.kernel.org/r/9b4bc4d59ba2e903b6a3eb17e16ef41a8e7b7c3e.1538603665.git.reinette.chatre@intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 72 ++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 643670fb8943..9d59ee1c444e 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -960,6 +960,78 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, return 0; } +/** + * rdt_cdp_peer_get - Retrieve CDP peer if it exists + * @r: RDT resource to which RDT domain @d belongs + * @d: Cache instance for which a CDP peer is requested + * @r_cdp: RDT resource that shares hardware with @r (RDT resource peer) + * Used to return the result. + * @d_cdp: RDT domain that shares hardware with @d (RDT domain peer) + * Used to return the result. + * + * RDT resources are managed independently and by extension the RDT domains + * (RDT resource instances) are managed independently also. The Code and + * Data Prioritization (CDP) RDT resources, while managed independently, + * could refer to the same underlying hardware. For example, + * RDT_RESOURCE_L2CODE and RDT_RESOURCE_L2DATA both refer to the L2 cache. + * + * When provided with an RDT resource @r and an instance of that RDT + * resource @d rdt_cdp_peer_get() will return if there is a peer RDT + * resource and the exact instance that shares the same hardware. + * + * Return: 0 if a CDP peer was found, <0 on error or if no CDP peer exists. + * If a CDP peer was found, @r_cdp will point to the peer RDT resource + * and @d_cdp will point to the peer RDT domain. + */ +static int __attribute__((unused)) rdt_cdp_peer_get(struct rdt_resource *r, + struct rdt_domain *d, + struct rdt_resource **r_cdp, + struct rdt_domain **d_cdp) +{ + struct rdt_resource *_r_cdp = NULL; + struct rdt_domain *_d_cdp = NULL; + int ret = 0; + + switch (r->rid) { + case RDT_RESOURCE_L3DATA: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3CODE]; + break; + case RDT_RESOURCE_L3CODE: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L3DATA]; + break; + case RDT_RESOURCE_L2DATA: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2CODE]; + break; + case RDT_RESOURCE_L2CODE: + _r_cdp = &rdt_resources_all[RDT_RESOURCE_L2DATA]; + break; + default: + ret = -ENOENT; + goto out; + } + + /* + * When a new CPU comes online and CDP is enabled then the new + * RDT domains (if any) associated with both CDP RDT resources + * are added in the same CPU online routine while the + * rdtgroup_mutex is held. It should thus not happen for one + * RDT domain to exist and be associated with its RDT CDP + * resource but there is no RDT domain associated with the + * peer RDT CDP resource. Hence the WARN. + */ + _d_cdp = rdt_find_domain(_r_cdp, d->id, NULL); + if (WARN_ON(!_d_cdp)) { + _r_cdp = NULL; + ret = -EINVAL; + } + +out: + *r_cdp = _r_cdp; + *d_cdp = _d_cdp; + + return ret; +} + /** * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other * @r: Resource to which domain instance @d belongs. -- cgit v1.2.3 From e5f3530c391105fdd6174852e3ea6136d073b45a Mon Sep 17 00:00:00 2001 From: Reinette Chatre Date: Wed, 3 Oct 2018 15:17:02 -0700 Subject: x86/intel_rdt: CBM overlap should also check for overlap with CDP peer The CBM overlap test is used to manage the allocations of RDT resources where overlap is possible between resource groups. When a resource group is in exclusive mode then there should be no overlap between resource groups. The current overlap test only considers overlap between the same resources, for example, that usage of a RDT_RESOURCE_L2DATA resource in one resource group does not overlap with usage of a RDT_RESOURCE_L2DATA resource in another resource group. The problem with this is that it allows overlap between a RDT_RESOURCE_L2DATA resource in one resource group with a RDT_RESOURCE_L2CODE resource in another resource group - even if both resource groups are in exclusive mode. This is a problem because even though these appear to be different resources they end up sharing the same underlying hardware and thus does not fulfill the user's request for exclusive use of hardware resources. Fix this by including the CDP peer (if there is one) in every CBM overlap test. This does not impact the overlap between resources within the same exclusive resource group that is allowed. Fixes: 49f7b4efa110 ("x86/intel_rdt: Enable setting of exclusive mode") Reported-by: Jithu Joseph Signed-off-by: Reinette Chatre Signed-off-by: Thomas Gleixner Tested-by: Jithu Joseph Acked-by: Fenghua Yu Cc: tony.luck@intel.com Cc: gavin.hindman@intel.com Cc: dave.hansen@intel.com Cc: hpa@zytor.com Link: https://lkml.kernel.org/r/e538b7f56f7ca15963dce2e00ac3be8edb8a68e1.1538603665.git.reinette.chatre@intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 48 +++++++++++++++++++++++++++----- 1 file changed, 41 insertions(+), 7 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 9d59ee1c444e..49c479822844 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -983,10 +983,9 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of, * If a CDP peer was found, @r_cdp will point to the peer RDT resource * and @d_cdp will point to the peer RDT domain. */ -static int __attribute__((unused)) rdt_cdp_peer_get(struct rdt_resource *r, - struct rdt_domain *d, - struct rdt_resource **r_cdp, - struct rdt_domain **d_cdp) +static int rdt_cdp_peer_get(struct rdt_resource *r, struct rdt_domain *d, + struct rdt_resource **r_cdp, + struct rdt_domain **d_cdp) { struct rdt_resource *_r_cdp = NULL; struct rdt_domain *_d_cdp = NULL; @@ -1033,7 +1032,7 @@ out: } /** - * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other + * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other * @r: Resource to which domain instance @d belongs. * @d: The domain instance for which @closid is being tested. * @cbm: Capacity bitmask being tested. @@ -1052,8 +1051,8 @@ out: * * Return: false if CBM does not overlap, true if it does. */ -bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, - unsigned long cbm, int closid, bool exclusive) +static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm, int closid, bool exclusive) { enum rdtgrp_mode mode; unsigned long ctrl_b; @@ -1088,6 +1087,41 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, return false; } +/** + * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware + * @r: Resource to which domain instance @d belongs. + * @d: The domain instance for which @closid is being tested. + * @cbm: Capacity bitmask being tested. + * @closid: Intended closid for @cbm. + * @exclusive: Only check if overlaps with exclusive resource groups + * + * Resources that can be allocated using a CBM can use the CBM to control + * the overlap of these allocations. rdtgroup_cmb_overlaps() is the test + * for overlap. Overlap test is not limited to the specific resource for + * which the CBM is intended though - when dealing with CDP resources that + * share the underlying hardware the overlap check should be performed on + * the CDP resource sharing the hardware also. + * + * Refer to description of __rdtgroup_cbm_overlaps() for the details of the + * overlap test. + * + * Return: true if CBM overlap detected, false if there is no overlap + */ +bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d, + unsigned long cbm, int closid, bool exclusive) +{ + struct rdt_resource *r_cdp; + struct rdt_domain *d_cdp; + + if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, exclusive)) + return true; + + if (rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp) < 0) + return false; + + return __rdtgroup_cbm_overlaps(r_cdp, d_cdp, cbm, closid, exclusive); +} + /** * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive * -- cgit v1.2.3 From 2a7adf6ce643fdeec051dc88e5250b08c83bbb67 Mon Sep 17 00:00:00 2001 From: Reinette Chatre Date: Wed, 3 Oct 2018 15:17:03 -0700 Subject: x86/intel_rdt: Fix initial allocation to consider CDP When a new resource group is created it is initialized with a default allocation that considers which portions of cache are currently available for sharing across all resource groups or which portions of cache are currently unused. If a CDP allocation forms part of a resource group that is in exclusive mode then it should be ensured that no new allocation overlaps with any resource that shares the underlying hardware. The current initial allocation does not take this sharing of hardware into account and a new allocation in a resource that shares the same hardware would affect the exclusive resource group. Fix this by considering the allocation of a peer RDT domain - a RDT domain sharing the same hardware - as part of the test to determine which portion of cache is in use and available for use. Fixes: 95f0b77efa57 ("x86/intel_rdt: Initialize new resource group with sane defaults") Signed-off-by: Reinette Chatre Signed-off-by: Thomas Gleixner Acked-by: Fenghua Yu Cc: tony.luck@intel.com Cc: jithu.joseph@intel.com Cc: gavin.hindman@intel.com Cc: dave.hansen@intel.com Cc: hpa@zytor.com Link: https://lkml.kernel.org/r/b1f7ec08b1695be067de416a4128466d49684317.1538603665.git.reinette.chatre@intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index 49c479822844..dbc7fc98b60a 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -2460,14 +2460,16 @@ static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r) */ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) { + struct rdt_resource *r_cdp = NULL; + struct rdt_domain *d_cdp = NULL; u32 used_b = 0, unused_b = 0; u32 closid = rdtgrp->closid; struct rdt_resource *r; unsigned long tmp_cbm; enum rdtgrp_mode mode; struct rdt_domain *d; + u32 peer_ctl, *ctrl; int i, ret; - u32 *ctrl; for_each_alloc_enabled_rdt_resource(r) { /* @@ -2477,6 +2479,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) if (r->rid == RDT_RESOURCE_MBA) continue; list_for_each_entry(d, &r->domains, list) { + rdt_cdp_peer_get(r, d, &r_cdp, &d_cdp); d->have_new_ctrl = false; d->new_ctrl = r->cache.shareable_bits; used_b = r->cache.shareable_bits; @@ -2486,9 +2489,19 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp) mode = rdtgroup_mode_by_closid(i); if (mode == RDT_MODE_PSEUDO_LOCKSETUP) break; - used_b |= *ctrl; + /* + * If CDP is active include peer + * domain's usage to ensure there + * is no overlap with an exclusive + * group. + */ + if (d_cdp) + peer_ctl = d_cdp->ctrl_val[i]; + else + peer_ctl = 0; + used_b |= *ctrl | peer_ctl; if (mode == RDT_MODE_SHAREABLE) - d->new_ctrl |= *ctrl; + d->new_ctrl |= *ctrl | peer_ctl; } } if (d->plr && d->plr->cbm > 0) -- cgit v1.2.3 From b61b8bba18fe2b63d38fdaf9b83de25e2d787dfe Mon Sep 17 00:00:00 2001 From: Jithu Joseph Date: Fri, 12 Oct 2018 15:51:01 -0700 Subject: x86/intel_rdt: Prevent pseudo-locking from using stale pointers When the last CPU in an rdt_domain goes offline, its rdt_domain struct gets freed. Current pseudo-locking code is unaware of this scenario and tries to dereference the freed structure in a few places. Add checks to prevent pseudo-locking code from doing this. While further work is needed to seamlessly restore resource groups (not just pseudo-locking) to their configuration when the domain is brought back online, the immediate issue of invalid pointers is addressed here. Fixes: f4e80d67a5274 ("x86/intel_rdt: Resctrl files reflect pseudo-locked information") Fixes: 443810fe61605 ("x86/intel_rdt: Create debugfs files for pseudo-locking testing") Fixes: 746e08590b864 ("x86/intel_rdt: Create character device exposing pseudo-locked region") Fixes: 33dc3e410a0d9 ("x86/intel_rdt: Make CPU information accessible for pseudo-locked regions") Signed-off-by: Jithu Joseph Signed-off-by: Reinette Chatre Signed-off-by: Thomas Gleixner Cc: fenghua.yu@intel.com Cc: tony.luck@intel.com Cc: gavin.hindman@intel.com Cc: hpa@zytor.com Link: https://lkml.kernel.org/r/231f742dbb7b00a31cc104416860e27dba6b072d.1539384145.git.reinette.chatre@intel.com --- arch/x86/kernel/cpu/intel_rdt.c | 7 ++++++ arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c | 12 +++++++-- arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 10 ++++++++ arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 38 +++++++++++++++++++++-------- 4 files changed, 55 insertions(+), 12 deletions(-) (limited to 'arch/x86/kernel') diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c index 1214f3f7ec6d..44272b7107ad 100644 --- a/arch/x86/kernel/cpu/intel_rdt.c +++ b/arch/x86/kernel/cpu/intel_rdt.c @@ -608,6 +608,13 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cancel_delayed_work(&d->cqm_limbo); } + /* + * rdt_domain "d" is going to be freed below, so clear + * its pointer from pseudo_lock_region struct. + */ + if (d->plr) + d->plr->d = NULL; + kfree(d->ctrl_val); kfree(d->mbps_val); bitmap_free(d->rmid_busy_llc); diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c index 0f53049719cd..27937458c231 100644 --- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c +++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c @@ -404,8 +404,16 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, for_each_alloc_enabled_rdt_resource(r) seq_printf(s, "%s:uninitialized\n", r->name); } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { - seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name, - rdtgrp->plr->d->id, rdtgrp->plr->cbm); + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + seq_printf(s, "%s:%d=%x\n", + rdtgrp->plr->r->name, + rdtgrp->plr->d->id, + rdtgrp->plr->cbm); + } } else { closid = rdtgrp->closid; for_each_alloc_enabled_rdt_resource(r) { diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c index 41aeb431e834..966ac0c20d67 100644 --- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c +++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c @@ -1174,6 +1174,11 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel) goto out; } + if (!plr->d) { + ret = -ENODEV; + goto out; + } + plr->thread_done = 0; cpu = cpumask_first(&plr->d->cpu_mask); if (!cpu_online(cpu)) { @@ -1494,6 +1499,11 @@ static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma) plr = rdtgrp->plr; + if (!plr->d) { + mutex_unlock(&rdtgroup_mutex); + return -ENODEV; + } + /* * Task is required to run with affinity to the cpus associated * with the pseudo-locked region. If this is not the case the task diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c index dbc7fc98b60a..f27b8115ffa2 100644 --- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c +++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c @@ -268,17 +268,27 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of, struct seq_file *s, void *v) { struct rdtgroup *rdtgrp; + struct cpumask *mask; int ret = 0; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (rdtgrp) { - if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) - seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", - cpumask_pr_args(&rdtgrp->plr->d->cpu_mask)); - else + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + mask = &rdtgrp->plr->d->cpu_mask; + seq_printf(s, is_cpu_list(of) ? + "%*pbl\n" : "%*pb\n", + cpumask_pr_args(mask)); + } + } else { seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n", cpumask_pr_args(&rdtgrp->cpu_mask)); + } } else { ret = -ENOENT; } @@ -1282,6 +1292,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, struct rdt_resource *r; struct rdt_domain *d; unsigned int size; + int ret = 0; bool sep; u32 ctrl; @@ -1292,11 +1303,18 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, } if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) { - seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name); - size = rdtgroup_cbm_to_size(rdtgrp->plr->r, - rdtgrp->plr->d, - rdtgrp->plr->cbm); - seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + if (!rdtgrp->plr->d) { + rdt_last_cmd_clear(); + rdt_last_cmd_puts("Cache domain offline\n"); + ret = -ENODEV; + } else { + seq_printf(s, "%*s:", max_name_width, + rdtgrp->plr->r->name); + size = rdtgroup_cbm_to_size(rdtgrp->plr->r, + rdtgrp->plr->d, + rdtgrp->plr->cbm); + seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size); + } goto out; } @@ -1326,7 +1344,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of, out: rdtgroup_kn_unlock(of->kn); - return 0; + return ret; } /* rdtgroup information files for one cache resource. */ -- cgit v1.2.3