Commit 292841b0 authored by Ian Munsie's avatar Ian Munsie Committed by Michael Ellerman

cxl: Update process element after allocating interrupts

In the kernel API, it is possible to attempt to allocate AFU interrupts
after already starting a context. Since the process element structure
used by the hardware is only filled out at the time the context is
started, it will not be updated with the interrupt numbers that have
just been allocated and therefore AFU interrupts will not work unless
they were allocated prior to starting the context.

This can present some difficulties as each CAPI enabled PCI device in
the kernel API has a default context, which may need to be started very
early to enable translations, potentially before interrupts can easily
be set up.

This patch makes the API more flexible to allow interrupts to be
allocated after a context has already been started and takes care of
updating the PE structure used by the hardware and notifying it to
discard any cached copy it may have.

The update is currently performed via a terminate/remove/add sequence.
This is necessary on some hardware such as the XSL that does not
properly support the update LLCMD.

Note that this is only supported on powernv at present - attempting to
perform this ordering on PowerVM will raise a warning.
Signed-off-by: default avatarIan Munsie <imunsie@au1.ibm.com>
Reviewed-by: default avatarFrederic Barrat <fbarrat@linux.vnet.ibm.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
parent 64417a39
...@@ -102,7 +102,10 @@ int cxl_allocate_afu_irqs(struct cxl_context *ctx, int num) ...@@ -102,7 +102,10 @@ int cxl_allocate_afu_irqs(struct cxl_context *ctx, int num)
if (num == 0) if (num == 0)
num = ctx->afu->pp_irqs; num = ctx->afu->pp_irqs;
res = afu_allocate_irqs(ctx, num); res = afu_allocate_irqs(ctx, num);
if (!res && !cpu_has_feature(CPU_FTR_HVMODE)) { if (res)
return res;
if (!cpu_has_feature(CPU_FTR_HVMODE)) {
/* In a guest, the PSL interrupt is not multiplexed. It was /* In a guest, the PSL interrupt is not multiplexed. It was
* allocated above, and we need to set its handler * allocated above, and we need to set its handler
*/ */
...@@ -110,6 +113,13 @@ int cxl_allocate_afu_irqs(struct cxl_context *ctx, int num) ...@@ -110,6 +113,13 @@ int cxl_allocate_afu_irqs(struct cxl_context *ctx, int num)
if (hwirq) if (hwirq)
cxl_map_irq(ctx->afu->adapter, hwirq, cxl_ops->psl_interrupt, ctx, "psl"); cxl_map_irq(ctx->afu->adapter, hwirq, cxl_ops->psl_interrupt, ctx, "psl");
} }
if (ctx->status == STARTED) {
if (cxl_ops->update_ivtes)
cxl_ops->update_ivtes(ctx);
else WARN(1, "BUG: cxl_allocate_afu_irqs must be called prior to starting the context on this platform\n");
}
return res; return res;
} }
EXPORT_SYMBOL_GPL(cxl_allocate_afu_irqs); EXPORT_SYMBOL_GPL(cxl_allocate_afu_irqs);
......
...@@ -855,6 +855,7 @@ struct cxl_backend_ops { ...@@ -855,6 +855,7 @@ struct cxl_backend_ops {
int (*attach_process)(struct cxl_context *ctx, bool kernel, int (*attach_process)(struct cxl_context *ctx, bool kernel,
u64 wed, u64 amr); u64 wed, u64 amr);
int (*detach_process)(struct cxl_context *ctx); int (*detach_process)(struct cxl_context *ctx);
void (*update_ivtes)(struct cxl_context *ctx);
bool (*support_attributes)(const char *attr_name, enum cxl_attrs type); bool (*support_attributes)(const char *attr_name, enum cxl_attrs type);
bool (*link_ok)(struct cxl *cxl, struct cxl_afu *afu); bool (*link_ok)(struct cxl *cxl, struct cxl_afu *afu);
void (*release_afu)(struct device *dev); void (*release_afu)(struct device *dev);
......
...@@ -1182,6 +1182,7 @@ const struct cxl_backend_ops cxl_guest_ops = { ...@@ -1182,6 +1182,7 @@ const struct cxl_backend_ops cxl_guest_ops = {
.ack_irq = guest_ack_irq, .ack_irq = guest_ack_irq,
.attach_process = guest_attach_process, .attach_process = guest_attach_process,
.detach_process = guest_detach_process, .detach_process = guest_detach_process,
.update_ivtes = NULL,
.support_attributes = guest_support_attributes, .support_attributes = guest_support_attributes,
.link_ok = guest_link_ok, .link_ok = guest_link_ok,
.release_afu = guest_release_afu, .release_afu = guest_release_afu,
......
...@@ -430,7 +430,6 @@ static int remove_process_element(struct cxl_context *ctx) ...@@ -430,7 +430,6 @@ static int remove_process_element(struct cxl_context *ctx)
return rc; return rc;
} }
void cxl_assign_psn_space(struct cxl_context *ctx) void cxl_assign_psn_space(struct cxl_context *ctx)
{ {
if (!ctx->afu->pp_size || ctx->master) { if (!ctx->afu->pp_size || ctx->master) {
...@@ -507,10 +506,39 @@ static u64 calculate_sr(struct cxl_context *ctx) ...@@ -507,10 +506,39 @@ static u64 calculate_sr(struct cxl_context *ctx)
return sr; return sr;
} }
static void update_ivtes_directed(struct cxl_context *ctx)
{
bool need_update = (ctx->status == STARTED);
int r;
if (need_update) {
WARN_ON(terminate_process_element(ctx));
WARN_ON(remove_process_element(ctx));
}
for (r = 0; r < CXL_IRQ_RANGES; r++) {
ctx->elem->ivte_offsets[r] = cpu_to_be16(ctx->irqs.offset[r]);
ctx->elem->ivte_ranges[r] = cpu_to_be16(ctx->irqs.range[r]);
}
/*
* Theoretically we could use the update llcmd, instead of a
* terminate/remove/add (or if an atomic update was required we could
* do a suspend/update/resume), however it seems there might be issues
* with the update llcmd on some cards (including those using an XSL on
* an ASIC) so for now it's safest to go with the commands that are
* known to work. In the future if we come across a situation where the
* card may be performing transactions using the same PE while we are
* doing this update we might need to revisit this.
*/
if (need_update)
WARN_ON(add_process_element(ctx));
}
static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr) static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
{ {
u32 pid; u32 pid;
int r, result; int result;
cxl_assign_psn_space(ctx); cxl_assign_psn_space(ctx);
...@@ -545,10 +573,7 @@ static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr) ...@@ -545,10 +573,7 @@ static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
ctx->irqs.range[0] = 1; ctx->irqs.range[0] = 1;
} }
for (r = 0; r < CXL_IRQ_RANGES; r++) { update_ivtes_directed(ctx);
ctx->elem->ivte_offsets[r] = cpu_to_be16(ctx->irqs.offset[r]);
ctx->elem->ivte_ranges[r] = cpu_to_be16(ctx->irqs.range[r]);
}
ctx->elem->common.amr = cpu_to_be64(amr); ctx->elem->common.amr = cpu_to_be64(amr);
ctx->elem->common.wed = cpu_to_be64(wed); ctx->elem->common.wed = cpu_to_be64(wed);
...@@ -600,6 +625,22 @@ static int activate_dedicated_process(struct cxl_afu *afu) ...@@ -600,6 +625,22 @@ static int activate_dedicated_process(struct cxl_afu *afu)
return cxl_chardev_d_afu_add(afu); return cxl_chardev_d_afu_add(afu);
} }
static void update_ivtes_dedicated(struct cxl_context *ctx)
{
struct cxl_afu *afu = ctx->afu;
cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An,
(((u64)ctx->irqs.offset[0] & 0xffff) << 48) |
(((u64)ctx->irqs.offset[1] & 0xffff) << 32) |
(((u64)ctx->irqs.offset[2] & 0xffff) << 16) |
((u64)ctx->irqs.offset[3] & 0xffff));
cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, (u64)
(((u64)ctx->irqs.range[0] & 0xffff) << 48) |
(((u64)ctx->irqs.range[1] & 0xffff) << 32) |
(((u64)ctx->irqs.range[2] & 0xffff) << 16) |
((u64)ctx->irqs.range[3] & 0xffff));
}
static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr) static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr)
{ {
struct cxl_afu *afu = ctx->afu; struct cxl_afu *afu = ctx->afu;
...@@ -618,16 +659,7 @@ static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr) ...@@ -618,16 +659,7 @@ static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr)
cxl_prefault(ctx, wed); cxl_prefault(ctx, wed);
cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An, update_ivtes_dedicated(ctx);
(((u64)ctx->irqs.offset[0] & 0xffff) << 48) |
(((u64)ctx->irqs.offset[1] & 0xffff) << 32) |
(((u64)ctx->irqs.offset[2] & 0xffff) << 16) |
((u64)ctx->irqs.offset[3] & 0xffff));
cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, (u64)
(((u64)ctx->irqs.range[0] & 0xffff) << 48) |
(((u64)ctx->irqs.range[1] & 0xffff) << 32) |
(((u64)ctx->irqs.range[2] & 0xffff) << 16) |
((u64)ctx->irqs.range[3] & 0xffff));
cxl_p2n_write(afu, CXL_PSL_AMR_An, amr); cxl_p2n_write(afu, CXL_PSL_AMR_An, amr);
...@@ -709,6 +741,15 @@ static inline int detach_process_native_dedicated(struct cxl_context *ctx) ...@@ -709,6 +741,15 @@ static inline int detach_process_native_dedicated(struct cxl_context *ctx)
return 0; return 0;
} }
static void native_update_ivtes(struct cxl_context *ctx)
{
if (ctx->afu->current_mode == CXL_MODE_DIRECTED)
return update_ivtes_directed(ctx);
if (ctx->afu->current_mode == CXL_MODE_DEDICATED)
return update_ivtes_dedicated(ctx);
WARN(1, "native_update_ivtes: Bad mode\n");
}
static inline int detach_process_native_afu_directed(struct cxl_context *ctx) static inline int detach_process_native_afu_directed(struct cxl_context *ctx)
{ {
if (!ctx->pe_inserted) if (!ctx->pe_inserted)
...@@ -1128,6 +1169,7 @@ const struct cxl_backend_ops cxl_native_ops = { ...@@ -1128,6 +1169,7 @@ const struct cxl_backend_ops cxl_native_ops = {
.irq_wait = native_irq_wait, .irq_wait = native_irq_wait,
.attach_process = native_attach_process, .attach_process = native_attach_process,
.detach_process = native_detach_process, .detach_process = native_detach_process,
.update_ivtes = native_update_ivtes,
.support_attributes = native_support_attributes, .support_attributes = native_support_attributes,
.link_ok = cxl_adapter_link_ok, .link_ok = cxl_adapter_link_ok,
.release_afu = cxl_pci_release_afu, .release_afu = cxl_pci_release_afu,
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment