diff options
Diffstat (limited to 'arch/powerpc/platforms/pseries/vas.c')
-rw-r--r-- | arch/powerpc/platforms/pseries/vas.c | 500 |
1 files changed, 465 insertions, 35 deletions
diff --git a/arch/powerpc/platforms/pseries/vas.c b/arch/powerpc/platforms/pseries/vas.c index d243ddc58827..1f59d78c77a1 100644 --- a/arch/powerpc/platforms/pseries/vas.c +++ b/arch/powerpc/platforms/pseries/vas.c @@ -26,9 +26,11 @@ static struct vas_all_caps caps_all; static bool copypaste_feat; +static struct hv_vas_cop_feat_caps hv_cop_caps; static struct vas_caps vascaps[VAS_MAX_FEAT_TYPE]; static DEFINE_MUTEX(vas_pseries_mutex); +static bool migration_in_progress; static long hcall_return_busy_check(long rc) { @@ -107,7 +109,6 @@ static int h_deallocate_vas_window(u64 winid) static int h_modify_vas_window(struct pseries_vas_window *win) { long rc; - u32 lpid = mfspr(SPRN_PID); /* * AMR value is not supported in Linux VAS implementation. @@ -115,7 +116,7 @@ static int h_modify_vas_window(struct pseries_vas_window *win) */ do { rc = plpar_hcall_norets(H_MODIFY_VAS_WINDOW, - win->vas_win.winid, lpid, 0, + win->vas_win.winid, win->pid, 0, VAS_MOD_WIN_FLAGS, 0); rc = hcall_return_busy_check(rc); @@ -124,8 +125,8 @@ static int h_modify_vas_window(struct pseries_vas_window *win) if (rc == H_SUCCESS) return 0; - pr_err("H_MODIFY_VAS_WINDOW error: %ld, winid %u lpid %u\n", - rc, win->vas_win.winid, lpid); + pr_err("H_MODIFY_VAS_WINDOW error: %ld, winid %u pid %u\n", + rc, win->vas_win.winid, win->pid); return -EIO; } @@ -310,8 +311,8 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, cop_feat_caps = &caps->caps; - if (atomic_inc_return(&cop_feat_caps->used_lpar_creds) > - atomic_read(&cop_feat_caps->target_lpar_creds)) { + if (atomic_inc_return(&cop_feat_caps->nr_used_credits) > + atomic_read(&cop_feat_caps->nr_total_credits)) { pr_err("Credits are not available to allocate window\n"); rc = -EINVAL; goto out; @@ -338,6 +339,8 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, } } + txwin->pid = mfspr(SPRN_PID); + /* * Allocate / Deallocate window hcalls and setup / free IRQs * have to be protected with mutex. @@ -354,7 +357,10 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, * same fault IRQ is not freed by the OS before. */ mutex_lock(&vas_pseries_mutex); - rc = allocate_setup_window(txwin, (u64 *)&domain[0], + if (migration_in_progress) + rc = -EBUSY; + else + rc = allocate_setup_window(txwin, (u64 *)&domain[0], cop_feat_caps->win_type); mutex_unlock(&vas_pseries_mutex); if (rc) @@ -369,13 +375,28 @@ static struct vas_window *vas_allocate_window(int vas_id, u64 flags, if (rc) goto out_free; - vas_user_win_add_mm_context(&txwin->vas_win.task_ref); txwin->win_type = cop_feat_caps->win_type; mutex_lock(&vas_pseries_mutex); - list_add(&txwin->win_list, &caps->list); + /* + * Possible to lose the acquired credit with DLPAR core + * removal after the window is opened. So if there are any + * closed windows (means with lost credits), do not give new + * window to user space. New windows will be opened only + * after the existing windows are reopened when credits are + * available. + */ + if (!caps->nr_close_wins) { + list_add(&txwin->win_list, &caps->list); + caps->nr_open_windows++; + mutex_unlock(&vas_pseries_mutex); + vas_user_win_add_mm_context(&txwin->vas_win.task_ref); + return &txwin->vas_win; + } mutex_unlock(&vas_pseries_mutex); - return &txwin->vas_win; + put_vas_user_win_ref(&txwin->vas_win.task_ref); + rc = -EBUSY; + pr_err("No credit is available to allocate window\n"); out_free: /* @@ -385,7 +406,7 @@ out_free: free_irq_setup(txwin); h_deallocate_vas_window(txwin->vas_win.winid); out: - atomic_dec(&cop_feat_caps->used_lpar_creds); + atomic_dec(&cop_feat_caps->nr_used_credits); kfree(txwin); return ERR_PTR(rc); } @@ -438,14 +459,25 @@ static int vas_deallocate_window(struct vas_window *vwin) caps = &vascaps[win->win_type].caps; mutex_lock(&vas_pseries_mutex); - rc = deallocate_free_window(win); - if (rc) { - mutex_unlock(&vas_pseries_mutex); - return rc; - } + /* + * VAS window is already closed in the hypervisor when + * lost the credit or with migration. So just remove the entry + * from the list, remove task references and free vas_window + * struct. + */ + if (!(win->vas_win.status & VAS_WIN_NO_CRED_CLOSE) && + !(win->vas_win.status & VAS_WIN_MIGRATE_CLOSE)) { + rc = deallocate_free_window(win); + if (rc) { + mutex_unlock(&vas_pseries_mutex); + return rc; + } + } else + vascaps[win->win_type].nr_close_wins--; list_del(&win->win_list); - atomic_dec(&caps->used_lpar_creds); + atomic_dec(&caps->nr_used_credits); + vascaps[win->win_type].nr_open_windows--; mutex_unlock(&vas_pseries_mutex); put_vas_user_win_ref(&vwin->task_ref); @@ -500,6 +532,7 @@ static int __init get_vas_capabilities(u8 feat, enum vas_cop_feat_type type, memset(vcaps, 0, sizeof(*vcaps)); INIT_LIST_HEAD(&vcaps->list); + vcaps->feat = feat; caps = &vcaps->caps; rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, feat, @@ -521,7 +554,7 @@ static int __init get_vas_capabilities(u8 feat, enum vas_cop_feat_type type, } caps->max_lpar_creds = be16_to_cpu(hv_caps->max_lpar_creds); caps->max_win_creds = be16_to_cpu(hv_caps->max_win_creds); - atomic_set(&caps->target_lpar_creds, + atomic_set(&caps->nr_total_credits, be16_to_cpu(hv_caps->target_lpar_creds)); if (feat == VAS_GZIP_DEF_FEAT) { caps->def_lpar_creds = be16_to_cpu(hv_caps->def_lpar_creds); @@ -533,16 +566,409 @@ static int __init get_vas_capabilities(u8 feat, enum vas_cop_feat_type type, } } + rc = sysfs_add_vas_caps(caps); + if (rc) + return rc; + copypaste_feat = true; return 0; } +/* + * VAS windows can be closed due to lost credits when the core is + * removed. So reopen them if credits are available due to DLPAR + * core add and set the window active status. When NX sees the page + * fault on the unmapped paste address, the kernel handles the fault + * by setting the remapping to new paste address if the window is + * active. + */ +static int reconfig_open_windows(struct vas_caps *vcaps, int creds, + bool migrate) +{ + long domain[PLPAR_HCALL9_BUFSIZE] = {VAS_DEFAULT_DOMAIN_ID}; + struct vas_cop_feat_caps *caps = &vcaps->caps; + struct pseries_vas_window *win = NULL, *tmp; + int rc, mv_ents = 0; + int flag; + + /* + * Nothing to do if there are no closed windows. + */ + if (!vcaps->nr_close_wins) + return 0; + + /* + * For the core removal, the hypervisor reduces the credits + * assigned to the LPAR and the kernel closes VAS windows + * in the hypervisor depends on reduced credits. The kernel + * uses LIFO (the last windows that are opened will be closed + * first) and expects to open in the same order when credits + * are available. + * For example, 40 windows are closed when the LPAR lost 2 cores + * (dedicated). If 1 core is added, this LPAR can have 20 more + * credits. It means the kernel can reopen 20 windows. So move + * 20 entries in the VAS windows lost and reopen next 20 windows. + * For partition migration, reopen all windows that are closed + * during resume. + */ + if ((vcaps->nr_close_wins > creds) && !migrate) + mv_ents = vcaps->nr_close_wins - creds; + + list_for_each_entry_safe(win, tmp, &vcaps->list, win_list) { + if (!mv_ents) + break; + + mv_ents--; + } + + /* + * Open windows if they are closed only with migration or + * DLPAR (lost credit) before. + */ + if (migrate) + flag = VAS_WIN_MIGRATE_CLOSE; + else + flag = VAS_WIN_NO_CRED_CLOSE; + + list_for_each_entry_safe_from(win, tmp, &vcaps->list, win_list) { + /* + * This window is closed with DLPAR and migration events. + * So reopen the window with the last event. + * The user space is not suspended with the current + * migration notifier. So the user space can issue DLPAR + * CPU hotplug while migration in progress. In this case + * this window will be opened with the last event. + */ + if ((win->vas_win.status & VAS_WIN_NO_CRED_CLOSE) && + (win->vas_win.status & VAS_WIN_MIGRATE_CLOSE)) { + win->vas_win.status &= ~flag; + continue; + } + + /* + * Nothing to do on this window if it is not closed + * with this flag + */ + if (!(win->vas_win.status & flag)) + continue; + + rc = allocate_setup_window(win, (u64 *)&domain[0], + caps->win_type); + if (rc) + return rc; + + rc = h_modify_vas_window(win); + if (rc) + goto out; + + mutex_lock(&win->vas_win.task_ref.mmap_mutex); + /* + * Set window status to active + */ + win->vas_win.status &= ~flag; + mutex_unlock(&win->vas_win.task_ref.mmap_mutex); + win->win_type = caps->win_type; + if (!--vcaps->nr_close_wins) + break; + } + + return 0; +out: + /* + * Window modify HCALL failed. So close the window to the + * hypervisor and return. + */ + free_irq_setup(win); + h_deallocate_vas_window(win->vas_win.winid); + return rc; +} + +/* + * The hypervisor reduces the available credits if the LPAR lost core. It + * means the excessive windows should not be active and the user space + * should not be using these windows to send compression requests to NX. + * So the kernel closes the excessive windows and unmap the paste address + * such that the user space receives paste instruction failure. Then up to + * the user space to fall back to SW compression and manage with the + * existing windows. + */ +static int reconfig_close_windows(struct vas_caps *vcap, int excess_creds, + bool migrate) +{ + struct pseries_vas_window *win, *tmp; + struct vas_user_win_ref *task_ref; + struct vm_area_struct *vma; + int rc = 0, flag; + + if (migrate) + flag = VAS_WIN_MIGRATE_CLOSE; + else + flag = VAS_WIN_NO_CRED_CLOSE; + + list_for_each_entry_safe(win, tmp, &vcap->list, win_list) { + /* + * This window is already closed due to lost credit + * or for migration before. Go for next window. + * For migration, nothing to do since this window + * closed for DLPAR and will be reopened even on + * the destination system with other DLPAR operation. + */ + if ((win->vas_win.status & VAS_WIN_MIGRATE_CLOSE) || + (win->vas_win.status & VAS_WIN_NO_CRED_CLOSE)) { + win->vas_win.status |= flag; + continue; + } + + task_ref = &win->vas_win.task_ref; + mutex_lock(&task_ref->mmap_mutex); + vma = task_ref->vma; + /* + * Number of available credits are reduced, So select + * and close windows. + */ + win->vas_win.status |= flag; + + mmap_write_lock(task_ref->mm); + /* + * vma is set in the original mapping. But this mapping + * is done with mmap() after the window is opened with ioctl. + * so we may not see the original mapping if the core remove + * is done before the original mmap() and after the ioctl. + */ + if (vma) + zap_page_range(vma, vma->vm_start, + vma->vm_end - vma->vm_start); + + mmap_write_unlock(task_ref->mm); + mutex_unlock(&task_ref->mmap_mutex); + /* + * Close VAS window in the hypervisor, but do not + * free vas_window struct since it may be reused + * when the credit is available later (DLPAR with + * adding cores). This struct will be used + * later when the process issued with close(FD). + */ + rc = deallocate_free_window(win); + /* + * This failure is from the hypervisor. + * No way to stop migration for these failures. + * So ignore error and continue closing other windows. + */ + if (rc && !migrate) + return rc; + + vcap->nr_close_wins++; + + /* + * For migration, do not depend on lpar_creds in case if + * mismatch with the hypervisor value (should not happen). + * So close all active windows in the list and will be + * reopened windows based on the new lpar_creds on the + * destination system during resume. + */ + if (!migrate && !--excess_creds) + break; + } + + return 0; +} + +/* + * Get new VAS capabilities when the core add/removal configuration + * changes. Reconfig window configurations based on the credits + * availability from this new capabilities. + */ +int vas_reconfig_capabilties(u8 type) +{ + struct vas_cop_feat_caps *caps; + int old_nr_creds, new_nr_creds; + struct vas_caps *vcaps; + int rc = 0, nr_active_wins; + + if (type >= VAS_MAX_FEAT_TYPE) { + pr_err("Invalid credit type %d\n", type); + return -EINVAL; + } + + vcaps = &vascaps[type]; + caps = &vcaps->caps; + + mutex_lock(&vas_pseries_mutex); + rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, vcaps->feat, + (u64)virt_to_phys(&hv_cop_caps)); + if (rc) + goto out; + + new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); + + old_nr_creds = atomic_read(&caps->nr_total_credits); + + atomic_set(&caps->nr_total_credits, new_nr_creds); + /* + * The total number of available credits may be decreased or + * inceased with DLPAR operation. Means some windows have to be + * closed / reopened. Hold the vas_pseries_mutex so that the + * the user space can not open new windows. + */ + if (old_nr_creds < new_nr_creds) { + /* + * If the existing target credits is less than the new + * target, reopen windows if they are closed due to + * the previous DLPAR (core removal). + */ + rc = reconfig_open_windows(vcaps, new_nr_creds - old_nr_creds, + false); + } else { + /* + * # active windows is more than new LPAR available + * credits. So close the excessive windows. + * On pseries, each window will have 1 credit. + */ + nr_active_wins = vcaps->nr_open_windows - vcaps->nr_close_wins; + if (nr_active_wins > new_nr_creds) + rc = reconfig_close_windows(vcaps, + nr_active_wins - new_nr_creds, + false); + } + +out: + mutex_unlock(&vas_pseries_mutex); + return rc; +} +/* + * Total number of default credits available (target_credits) + * in LPAR depends on number of cores configured. It varies based on + * whether processors are in shared mode or dedicated mode. + * Get the notifier when CPU configuration is changed with DLPAR + * operation so that get the new target_credits (vas default capabilities) + * and then update the existing windows usage if needed. + */ +static int pseries_vas_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct of_reconfig_data *rd = data; + struct device_node *dn = rd->dn; + const __be32 *intserv = NULL; + int len, rc = 0; + + if ((action == OF_RECONFIG_ATTACH_NODE) || + (action == OF_RECONFIG_DETACH_NODE)) + intserv = of_get_property(dn, "ibm,ppc-interrupt-server#s", + &len); + /* + * Processor config is not changed + */ + if (!intserv) + return NOTIFY_OK; + + rc = vas_reconfig_capabilties(VAS_GZIP_DEF_FEAT_TYPE); + if (rc) + pr_err("Failed reconfig VAS capabilities with DLPAR\n"); + + return rc; +} + +static struct notifier_block pseries_vas_nb = { + .notifier_call = pseries_vas_notifier, +}; + +/* + * For LPM, all windows have to be closed on the source partition + * before migration and reopen them on the destination partition + * after migration. So closing windows during suspend and + * reopen them during resume. + */ +int vas_migration_handler(int action) +{ + struct vas_cop_feat_caps *caps; + int old_nr_creds, new_nr_creds = 0; + struct vas_caps *vcaps; + int i, rc = 0; + + /* + * NX-GZIP is not enabled. Nothing to do for migration. + */ + if (!copypaste_feat) + return rc; + + mutex_lock(&vas_pseries_mutex); + + if (action == VAS_SUSPEND) + migration_in_progress = true; + else + migration_in_progress = false; + + for (i = 0; i < VAS_MAX_FEAT_TYPE; i++) { + vcaps = &vascaps[i]; + caps = &vcaps->caps; + old_nr_creds = atomic_read(&caps->nr_total_credits); + + rc = h_query_vas_capabilities(H_QUERY_VAS_CAPABILITIES, + vcaps->feat, + (u64)virt_to_phys(&hv_cop_caps)); + if (!rc) { + new_nr_creds = be16_to_cpu(hv_cop_caps.target_lpar_creds); + /* + * Should not happen. But incase print messages, close + * all windows in the list during suspend and reopen + * windows based on new lpar_creds on the destination + * system. + */ + if (old_nr_creds != new_nr_creds) { + pr_err("Target credits mismatch with the hypervisor\n"); + pr_err("state(%d): lpar creds: %d HV lpar creds: %d\n", + action, old_nr_creds, new_nr_creds); + pr_err("Used creds: %d, Active creds: %d\n", + atomic_read(&caps->nr_used_credits), + vcaps->nr_open_windows - vcaps->nr_close_wins); + } + } else { + pr_err("state(%d): Get VAS capabilities failed with %d\n", + action, rc); + /* + * We can not stop migration with the current lpm + * implementation. So continue closing all windows in + * the list (during suspend) and return without + * opening windows (during resume) if VAS capabilities + * HCALL failed. + */ + if (action == VAS_RESUME) + goto out; + } + + switch (action) { + case VAS_SUSPEND: + rc = reconfig_close_windows(vcaps, vcaps->nr_open_windows, + true); + break; + case VAS_RESUME: + atomic_set(&caps->nr_total_credits, new_nr_creds); + rc = reconfig_open_windows(vcaps, new_nr_creds, true); + break; + default: + /* should not happen */ + pr_err("Invalid migration action %d\n", action); + rc = -EINVAL; + goto out; + } + + /* + * Ignore errors during suspend and return for resume. + */ + if (rc && (action == VAS_RESUME)) + goto out; + } + +out: + mutex_unlock(&vas_pseries_mutex); + return rc; +} + static int __init pseries_vas_init(void) { - struct hv_vas_cop_feat_caps *hv_cop_caps; struct hv_vas_all_caps *hv_caps; - int rc; + int rc = 0; /* * Linux supports user space COPY/PASTE only with Radix @@ -566,35 +992,39 @@ static int __init pseries_vas_init(void) caps_all.descriptor = be64_to_cpu(hv_caps->descriptor); caps_all.feat_type = be64_to_cpu(hv_caps->feat_type); - hv_cop_caps = kmalloc(sizeof(*hv_cop_caps), GFP_KERNEL); - if (!hv_cop_caps) { - rc = -ENOMEM; - goto out; - } + sysfs_pseries_vas_init(&caps_all); + /* * QOS capabilities available */ if (caps_all.feat_type & VAS_GZIP_QOS_FEAT_BIT) { rc = get_vas_capabilities(VAS_GZIP_QOS_FEAT, - VAS_GZIP_QOS_FEAT_TYPE, hv_cop_caps); + VAS_GZIP_QOS_FEAT_TYPE, &hv_cop_caps); if (rc) - goto out_cop; + goto out; } /* * Default capabilities available */ - if (caps_all.feat_type & VAS_GZIP_DEF_FEAT_BIT) { + if (caps_all.feat_type & VAS_GZIP_DEF_FEAT_BIT) rc = get_vas_capabilities(VAS_GZIP_DEF_FEAT, - VAS_GZIP_DEF_FEAT_TYPE, hv_cop_caps); - if (rc) - goto out_cop; - } + VAS_GZIP_DEF_FEAT_TYPE, &hv_cop_caps); + + if (!rc && copypaste_feat) { + if (firmware_has_feature(FW_FEATURE_LPAR)) + of_reconfig_notifier_register(&pseries_vas_nb); - pr_info("GZIP feature is available\n"); + pr_info("GZIP feature is available\n"); + } else { + /* + * Should not happen, but only when get default + * capabilities HCALL failed. So disable copy paste + * feature. + */ + copypaste_feat = false; + } -out_cop: - kfree(hv_cop_caps); out: kfree(hv_caps); return rc; |